A deep dive into the machine learning models behind more accurate ETA predictions 

TL;DR 

• Many retailers still build delivery promises by combining a processing window, a carrier transit estimate, and a buffer. 
• That approach starts to break down in supplier-fulfilled ecommerce, where processing times vary by warehouse, backlog, fill rate, and current operating conditions. 
• Rithum’s Delivery Promise uses machine learning to predict processing time and transit time separately, which produces a more realistic ETA. 
• The advantage comes from the data behind the prediction, especially supplier-warehouse visibility across the network. 
• Package Predictor is separate from Delivery Promise, but it improves shipping-cost decisions by predicting package weight and dimensions more accurately. 

For a lot of retailers, delivery promise still starts with simple math: three days to process, five days in transit (call it eight) and move on. That kind of estimate can work for a while, especially when the fulfillment network is relatively predictable. But it gets shaky fast in supplier-fulfilled ecommerce, where one order may ship from a warehouse running normally, while the next may come from a location dealing with backlog, fill rate issues, or a completely different operating rhythm. 

Carrier performance adds another layer of variability, changing by service level, lane, and time of year. So, while a static estimate may look clean in the system, it can end up far removed from how an order is actually likely to travel. 

That is the problem that machine learning is helping solve in Rithum’s Delivery Promise. Instead of relying on one rule that tries to cover everything, Delivery Promise can use historical and real-time data to make a better estimate of how a given order will progress through fulfillment and transit. And because Rithum sits across a broad supplier network, the model can work from a fuller picture than most retailers have on their own. 

Why do static ETA estimates break down in supplier-fulfilled ecommerce networks?

Static promise logic assumes fulfillment behaves like a fixed process. In supplier-fulfilled ecommerce, it rarely does. 

If you are relying on a standard processing window and an average transit estimate, you are treating every order like it moves the same way when it doesn’t. Supplier performance is rarely consistent across the network; one warehouse may be operating normally while another is slowed by backlog, labor constraints, fill rate issues, or the type of orders coming through. 

You may not know ahead of time which warehouse will handle the order. That alone makes it tough to pin processing time to one standard number. 

A simple estimate is easy to put in place. Keeping it useful is another story once the network gets bigger and more complex. 

How does machine learning improve delivery promise accuracy?

Rithum’s approach starts by separating two questions that many systems treat as one. 

Delivery Promise uses predictive machine learning models to predict how long an order is likely to take to process before it ships and how long it is likely to take in transit after it leaves the warehouse. Those two steps are connected, but they are not driven by the same conditions. 

Processing time depends on what is happening inside the supplier’s operation. Transit time depends on what happens once the package is in the carrier network. Treating them separately gives you a more realistic ETA than rolling everything into one estimate. 

Rather than forcing every shipment through the same assumption, the system can use historical performance and current conditions to make a better prediction for the specific order in front of it. 

Why does Rithum’s network give the model a clearer view of ETA risk?

The model only gets you part of the way. ETA accuracy also depends on how much of the fulfillment picture the system can actually see. 

In supplier-fulfilled commerce, retailers are often working with gaps. They may know the supplier, but not the warehouse that will ship the order. Even when they know the likely location, they may not have a current view of backlog, fill rate, or how that warehouse has been performing under similar conditions. 

Rithum works from a broader set of signals across its network, including where inventory sits, which warehouse is likely to fulfill the order, how that location has performed in similar situations, and what current conditions look like in real time. 

That broader view is the real advantage. A retailer may know its own order history. Rithum can pair that with network-level visibility into supplier warehouses, which gives the model a stronger read on where risk is building and where a promise is more likely to hold. 

Why do more accurate delivery promises help at checkout?

At checkout, the estimate has to hold up. When the date is built from a simple estimate, retailers usually have to play it one of two ways: pad it to be safe, or tighten it and hope the order moves the way the system expects. Neither is a great option. 

With a better prediction behind it, the system can generate a date based on how that order is likely to move through fulfillment and transit under current conditions, rather than applying one broad assumption across the board. 

That gives retailers a better shot at posting a date that can hold up without pushing it farther out than necessary—protecting checkout conversion rates while safeguarding brand trust. 

What is Package Predictor, and how does it connect to Delivery Promise?

Package Predictor is related to Delivery Promise, but it is not doing the same job. 

Delivery Promise is trying to predict timing. Package Predictor is trying to predict how the shipment will actually be packaged, especially when it comes to weight and dimensions. 

That is a different problem, and it affects a different part of the shipping decision. The size of the box usually is not what determines how fast something moves through the network, but it does affect shipping cost and service selection. 

That is where things get messy in dropship. You may have catalog data for an item, but not enough detail to know how a real order will be packaged, especially when multiple items ship together. And when that data is coming from a broad supplier base, it’s often incomplete, inconsistent, or both. 

Package Predictor gives the system a better way to work through that uncertainty. It looks at historical shipment behavior and uses those patterns to make a better estimate than a manual default can. 

How does Package Predictor improve shipping-cost decisions?

Package Predictor gives the rate estimate better information to work from. If the estimated weight and dimensions are wrong, the estimated shipping cost is wrong. And once the cost estimate is off, it becomes much easier to choose the wrong service or make a fulfillment decision that costs more than expected. 

Package Predictor improves both accuracy and coverage, reducing the number of cases where the system has to fall back to broad supplier-level or retailer-level defaults. 

Better package estimates sharpen carrier-rate accuracy—and that’s what drives smarter shipping decisions. 

Why rising shipping complexity puts more pressure on ETA accuracy and package data

Shipping has gotten more expensive in more complicated ways. Carrier agreements are more layered than they used to be, dimensional-weight charges continue to hit certain shipments harder, and small inaccuracies in the data can create bigger downstream problems than they once did. 

That puts Delivery Promise and Package Predictor under a brighter light. One is trying to generate a delivery date that holds up in a more variable network. The other is trying to improve the package data behind the rate estimate, so the shipping decision is built on something more reliable than a rough default. 

When costs tighten and variability increases, the quality of those inputs is what ultimately protects your profit margins. 

What retailers should do next if static delivery estimates are starting to fall short

The old approach gets harder to trust as fulfillment spreads across more suppliers, more warehouses, and more moving parts. 

If you are trying to improve ETA accuracy in supplier-fulfilled ecommerce, broad averages only get you so far. Better predictions come from data that reflects how fulfillment and transit are actually performing. 

Machine learning becomes useful when it can model that day-to-day variation instead of smoothing it over with one broad rule. That is especially true in supplier networks, where the operating conditions behind an order can change from one warehouse to the next. 

The prediction is only as strong as the visibility behind it. The clearer the view into supplier warehouses, fulfillment conditions, and transit performance, the stronger the delivery promise becomes. 

To learn more about how Rithum supports delivery promise accuracy and shipping-cost decisions, schedule a demo for a closer look at Delivery Promise and Package Predictor. 

Kyle Knoblock is Staff Product Manager, Retailers at Rithum.

The post From guesswork to precision: How AI improves delivery promise accuracy appeared first on Rithum.

Ulta Beauty is now live on TikTok Shop, bringing one of retail’s most recognized beauty retailers into a channel where discovery and purchase increasingly happen side by side. 

For a retailer built on experience, assortment, and community, the move feels like a natural next step. TikTok Shop gives Ulta Beauty a new way to reach shoppers in the moment, when they are discovering a product for the first time, following a trend in real time, or ready to buy without leaving the platform. 

A new channel for beauty discovery, shopping, and growth 

The launch reflects a broader shift in how people shop. More consumers are finding products through content and expecting a faster path from inspiration to purchase. For Ulta Beauty, TikTok Shop offers a more direct path from discovery to checkout in a channel that is already shaping how beauty shoppers browse and buy. 

Rithum served as Ulta Beauty’s integration partner for the launch and ongoing management, supporting the work behind the scenes to bring the new channel to market. The launch builds on the long-standing relationship between the two companies. 

Ulta Beauty’s launch on TikTok Shop reflects how retailers are bringing discovery and purchase closer together. We’re proud to support Ulta Beauty as they expand into this channel and to build on the strong partnership we’ve established over time.

– Blaine Nielsen, President, Retailers at Rithum

The move gives Ulta Beauty a new way to connect with shoppers as they discover and buy on TikTok Shop. It also gives the retailer another way to reach new shoppers while deepening engagement with existing ones. 

A curated experience built for TikTok Shop 

Ulta Beauty’s TikTok Shop launch reflects that strategy through a curated experience designed for the platform, including exclusive bundles, early-access moments, and creator-led discovery. The result is a shop experience that feels native to TikTok while staying grounded in what customers already expect from Ulta Beauty. 

TikTok Shop is an exciting extension of Ulta Beauty’s discovery-led ecosystem, giving us another way to meet guests where the beauty conversation is happening and bring our trusted curation to life in a TikTok-native format. We see this as a complementary, incremental channel, and we appreciate Rithum’s partnership in bringing it to market.

– Josh Friedman, SVP, Digital and Ecommerce, Ulta Beauty

As social commerce continues to grow, TikTok Shop is becoming an increasingly important channel for retailers and brands that want to connect discovery and purchase more closely. Ulta Beauty’s launch extends its discovery-led approach into a new environment. 

The post Ulta Beauty enters TikTok Shop with Rithum as integration partner  appeared first on Rithum.

Retail is under pressure from every angle. Rising shipping costs are squeezing already tight margins, while consumer expectations for fast, reliable delivery continue to climb. And surcharges up to 26% push real costs above 10% for many shippers. 

Ecommerce retailers face even tougher challenges. Online return rates reached 24.5% this year, compared to just 8.71% for in-store purchases, according to the latest data from Capital One Shopping. This results in higher fulfillment costs and added strain on operations, challenging retailers to maintain speed and accuracy. 

For retailers operating dropship and private marketplace models, these challenges are multiplied. Managing hundreds of suppliers, each with different shipping capabilities and performance standards, while maintaining consistent customer experience, becomes an overwhelming task that traditionally requires a lot of manual work. 

Rithum’s Delivery Solutions are a comprehensive suite of automated tools. These tools are designed to help retailers of every size and shape cut shipping costs, improve delivery performance, and manage suppliers more effectively without the added headcount. Here’s how it works. 

Shipping Optimization: automated savings without the manual work 

Shipping Optimization is at the heart of Rithum’s Delivery Solutions. Rithum uses an intelligent system that automatically selects the best shipping method and origin for every order based on real-time data. Rather than guesswork, the system is powered by comprehensive data including supplier warehouse locations, current inventory levels, product specifications, and dynamic carrier rates. 

Retailers using Shipping Optimization can save 10 to 20% on their annual third-party shipping costs, especially for multicarrier strategies. This automation runs within Rithum’s dropship network, requiring zero IT integration while delivering substantial cost reductions.  

For one multi-brand home goods retailer managing dozens of suppliers across furniture, decor, and kitchen categories, that meant serious savings. With millions in annual shipping spend, a 10% reduction translates to seven-figure savings annually. That’s money that flows directly to the bottom line while the system operates autonomously in the background. 

While the underlying technology analyzes thousands of variables as they happen, your team experiences it as orders being routed more efficiently, costs dropping, and performance improving without any manual intervention. 

Delivery Promise: faster estimates that drive conversions 

Nothing kills a sale faster than uncertain or lengthy delivery timelines. Rithum’s Delivery Promise tackles this challenge directly by providing accurate delivery dates using sophisticated machine learning models that factor in supplier performance history, weather patterns, current order backlogs, and warehouse fill rates. 

Delivery Promise can improve metrics dramatically. Results depend on your starting point, goals, and implementation approach. We’ve achieved 95%+ early and on-time delivery accuracy with optimized promise dates and measured up to 18% conversion lift for each day removed from Delivery Promise. 

According to industry data from the Baynard Institute, 47% of shoppers abandon carts due to shipping costs. The connection to delivery promises is clear: show accurate, optimized delivery dates upfront with total costs, and you remove the uncertainty that kills conversions. 

Our machine learning models are continuously improving, learning from actual delivery performance to refine future predictions. This creates a virtuous cycle where delivery promises become more accurate over time, further improving customer confidence and conversion rates.  

Ensuring supplier compliance with End-to-End (E2E) Monitoring  

Managing supplier performance across a diverse network has traditionally required armies of analysts to constantly monitor shipment data, chase down exceptions, and manually create reports. E2E monitoring transforms this labor-intensive process into an automated oversight system, saving retailer time and resources. 

Real-time monitoring tracks every aspect of supplier shipping performance, automatically generating reports that provide visibility and accountability across your entire network. This systematic approach enables retailers to achieve 97% or higher SLA compliance across their supplier networks. That’s a level of performance that would be nearly impossible to maintain through manual processes alone. 

The downstream benefits extend far beyond internal operations. Improved supplier compliance directly reduces “Where Is My Order” (WISMO) customer service inquiries, minimizes negative reviews related to shipping delays, and prevents the last-minute scrambling that occurs when shipments go awry. 

With consistent performance standards across all suppliers, retailers can confidently make delivery promises to customers while knowing their supplier network will deliver on those commitments. Rithum documents how shipment and delivery insights expose exceptions early so teams can act before promises are missed. 

Released Q3 2025: Shipping Address Validation 

Rithum continues to develop Delivery Solutions to ease the fulfillment process and cut costs. Shipping address validation released Q3 2025. This feature helps prevent costly last-mile delivery errors. It verifies delivery addresses and classifying them as residential or commercial before shipment. The validation will reduce failed deliveries and the expensive redelivery attempts that follow, leading to significant savings for retailers. 

Address validation represents another layer of automated intelligence that further reduces costs and improves customer experience without requiring additional operational resources. 

Built for dropship and private marketplace complexity 

Traditional fulfillment models, while challenging, operate within relatively controlled environments. Dropship and private marketplace fulfillment introduces exponentially more complexity: hundreds of suppliers with varying capabilities, different shipping standards, multiple inventory systems, and fragmented communication channels. 

Rithum’s Delivery Solutions was purpose-built to handle this complexity. The platform connects disparate systems and automates manual decisions that would otherwise require constant human oversight. That provides retailers with comprehensive visibility across fragmented supplier networks, allowing them to make informed decisions.  

This approach transforms what has historically been a series of manual, error-prone processes into an automated system that scales as your supplier network grows. 

Bring delivery under control with Rithum 

Shipping Optimization, Delivery Promise, and End-to-End Monitoring work together to tackle three daily problems: rising parcel costs, higher shopper expectations, and complex third-party operations. 

Use them to lower shipping spend, give customers clear delivery dates, and keep suppliers on time, all without adding headcount. 

Package Predictor, powered by RithumIQ, automatically predicts package weights and dimensions based on real-world shipping behaviors. For retailers using Shipping Optimization, predictions flow into the label printing process to reduce manual guessing and avoid costly mis-selections. Accuracy stats are forthcoming once broader rollout data is in. 

Ready to see what 10-20% shipping savings looks like for your specific operation? We’ll analyze your historical shipping data—at no cost—to show exactly where dropship rate shopping could impact your bottom line. Contact us for your personalized savings analysis based on your actual shipping patterns and supplier network. 

Connect with Rithum to see what this looks like for your business. Get the tools and intelligence needed to succeed in today’s retail environment. 

Kyle Knoblock is Staff Product Manager, Retailers at Rithum.

The post How Rithum’s delivery solutions helps retailers save 10% on shipping costs—with no added headcount  appeared first on Rithum.

During Prime Days 2025, one client brand Rithum works with saw their conversion and average order value slide early. Instead of throwing more budget at weak campaigns, the team held spend, watched the data, and waited for cleaner signals. When performance improved later in the event, they pushed onward and finished strong. 

An apparel brand during the same period saw similar issues. But they decided not to wait. Reliable performance signals showed a shift toward back-to-school demand. So, the team pivoted mid-event and adjusted assortments to focus on back-to-school products, introduced bundle offers, and optimized product titles and keywords. That shift resulted in a 15% increase in sales year over year vs. the previous Prime Day. 

Both brands took different approaches, based on having the visibility and confidence to act on what the data was telling them. There wasn’t a one-size-fits-all approach, but the key was data and agility. 

But according to the 2026 commerce readiness index, a survey of 200 brand and retail leaders across the U.S. and U.K, many brands don’t have that level of confidence and visibility to make it work.

According to the survey data, economic instability and inflation are the top hurdles to market expansion for both retailers and brands. But close behind sit technology and data challenges, rising operational costs, shifting consumer behavior, and supply chain issues.  

Some of that drag is the market. But lot of it is self-inflicted. Using the survey responses from commerce leaders, these are the three internal drags you say you feel the most . . . and what you can about them. And one external headwind you can only prepare for. 

Hidden drag 1: Manual ecommerce operations that slow omnichannel growth 

This drag shows up in the everyday work that still runs on spreadsheets and email, even as your sales channels and partners multiply. 

According to the survey, leaders say they’re “stuck at spreadsheet speed.” Fully automated workflows are rare, with many retail and brand leaders saying that 26% to 50% of their workflows still rely on manual steps like spreadsheets and email. 

In practice, this might look like retail vendor analysts pulling late-order reports into Excel, pivoting them, emailing suppliers one by one, and manually editing product descriptions before listings go live. On the brand side, manual work often involves pulling performance signals from multiple platforms, reconciling conflicting reports in spreadsheets, and chasing analysts for validation before anyone can act. 

You can see the impact of that manual overload in the data. Nearly three quarters of leaders say they at least sometimes make decisions based on inaccurate or inconsistent data, and more than a third say it happens often or all the time. 

53% of retailers say they act on important performance signals within 48 hours; brands are more likely to need three to five business days. Even the fastest groups say they are still acting on incomplete or inconsistent data and largely manual processes. 

If you’re selling through marketplaces, dropship programs, retailer.com sites, and your own direct-to-consumer (D2C) website, this is more than an internal annoyance. Manual listing updates, inventory syncs, and routing decisions become the places where channels drift and small errors balloon across your entire network. 

To turn this drag into an advantage, teams are: 

• Automating onboarding of assortments, content updates, inventory synchronization, and order routing where possible. 

• Consolidating product, inventory, and order data so a change to a SKU is reflected wherever you sell it. 

• Replacing “hero” spreadsheets with shared rules and playbooks that run on current, accurate data. 

Hidden drag 2: AI running on messy product and inventory data 

This drag appears when AI is built on data that is incomplete, inconsistent, or scattered across systems. 

AI is already live for many of the retailers and brands surveyed. 41% of retailers and 29% of brands use AI-based automation across functions like pricing, inventory, and marketing, and another 57% of brands and 41% of retailers say they are getting ready to implement it. 

At the same time, nearly three in four leaders say AI is advancing faster than their organizations can apply it effectively. 

The gap is visible: 

• 49% of retailers and 62% of brands say they still struggle with too many manual processes. 

• 91% of retailers and 78% of brands say poor data quality is a challenge. 

The same leaders rolling out AI across pricing, inventory, and marketing are also telling us they don’t fully trust the data underneath it. When catalog attributes are inconsistent, stock numbers are unreliable, or order and return data live in different silos, AI trained on that information doesn’t fix the issues, it magnifies them. 

This can show up as: 

• Retail media campaigns bidding on SKUs that are already out of stock on key partners. 

• Pricing models making decisions based on incomplete fees or cost data in certain channels. 

• AI “optimizing” assortments based on stale sell-through and margin data. 

How to make AI actually useful 

Start by fixing the inputs. Clean up product data, improve inventory accuracy, and connect orders and returns back to their source channels so you know what really happened and where. 

Then shorten the path from insight to action. If every AI-driven price or bid suggestion still has to be pasted into a spreadsheet and debated in a meeting, you will never see the benefit.  

Apply AI where it matters most: margin pressure from fulfillment and logistics, inventory stock-outs, and wasted media on low-quality traffic. Those are natural places to focus AI, once the data is ready. 

Hidden drag 3: Margin erosion across marketplaces and retail media 

This drag shows up in the small gaps where money and customers slip away across channels. 

Brands say the biggest hits in the past year came from fulfilment, logistics, and product costs. Retailers point first to tariffs and trade disruptions. Both groups also call out discounts, paid media inefficiency, and listing errors or inaccurate product data as other margin drains. 

Retailers most often lose shoppers before checkout, especially when ads do not match the product experience or when payment fails. Brands are more likely to have problems after the sale, in customer care and returns or refunds. 

At the same time, 91% of retailers and 84% of brands say they have changed their marketing channel mix in the last year, often in response to shifting consumer behavior and strategy.  

Some examples where customers and profit are lost in operations: 

• Broken links or mismatched product pages that cause pre-checkout drop-off. 

• Ads driving to SKUs that are out of stock or unprofitable to ship once fees and costs are counted. 

• Returns and service policies that vary by channel, leaving some experiences noticeably worse. 

The fix is to connect performance metrics with operational and margin data to see where the problems really come from. Are you losing money because of traffic quality, or because of content, availability, or fulfillment issues that could be fixed centrally and rolled out across channels? 

The drag you can’t fix: External volatility and ecommerce expansion 

This force comes from outside your walls, but it still shapes how fast you can grow and where. 

When retail and brand leaders rank their top hurdles to expanding into new markets, economic instability and inflation come first for both. Close behind are technology and data challenges, rising operational costs, shifting consumer behavior, supply chain issues, regulatory complexity, and tariff or trade uncertainty. 

Tariffs in particular stand out. 46% of retailers and 60% of brands say they are at least somewhat concerned that tariff and trade shifts will disrupt their sourcing strategies. More than 60% of both groups say they are re-evaluating sourcing relationships to prepare, while many are also cutting business costs and investing in supply chain resilience. 

You cannot control that volatility. However, you can decide how much internal drag you stack on top of it. Focus on what you can change by building stronger operations, reducing technology barriers, and creating more flexible, integrated customer experiences so you can pivot channels, partners, and assortments when conditions change. 

For a deeper look at the data behind these drags and more benchmarks you can use in your own planning, download the full 2026 commerce readiness index report. 

The post Three hidden drags you can fix (and one you can’t) appeared first on Rithum.

Shoppers now ask AI assistants what they want to buy and get a short, curated list of recommendations with reasons, not a list of links to look up. Amazon’s Help Me Decide feature picks one product and explains why. Pinterest introduced a multimodal AI shopping assistant that turns voice, text, and image prompts into shoppable recommendations. Snap is building conversational search into Snapchat through a $400M partnership with Perplexity, bringing cited, in-chat answers to nearly a billion users starting in 2026. 

Assistant-led shopping is gaining ground, but The 2026 commerce readiness index, based on surveys of 200 global brand and retail executives, found that most retailers and brands are not ready. “Customer journeys are bleeding revenue. The cracks are everywhere: prospective shoppers bounce at broken links, irrelevant ads, and empty shelves, while current customers churn after bad service, costly returns, and radio silence from brands. Each leak bleeds profit.”  

Pouring more spend into acquisition won’t fix a leaky funnel. Instead, you must patch your highest-loss points first, then scale your spend to drive growth. 

Find the leaks first 

Before fixing anything, identify where journeys fail. According to the survey, retailers lose prospects before checkout. 26% point to gaps between ads and products, and 19% to payment processing issues. 

But brands lose customers after the sale. 22% cite customer care problems and 17% point to returns and refunds. 

These two realities suggest a practical order of work: stabilize pre-checkout for retailers and post-purchase for brands, supported by clean data and responsive operations. 

Why leaks persist (and why “move fast” isn’t enough) 

The index shows that while retailers and brands say they want to move quickly, their inputs and workflows slow them down. “Fully automated workflows are almost nonexistent,” according to the survey respondents. 

While 99% of brands and 100% of retailers say they feel confident measuring performance, high confidence is not the same as accuracy. Nearly 75% of brands and retailers admit they sometimes make decisions based on inaccurate data. And more than one-third say it happens “often” or “all the time.” 

These leaks are not random. They come from manual processes and imperfect data. Fix the inputs to steady the buyer journey. 

Start with these four leaks 

Start with the biggest-loss points. Each fix will reinforce the next. 

1. Ad → product page 
   26% of retailers said ad-to-product gaps proved most problematic. To fix it, make ads match reality. Tie placements to real-time catalog data: titles, images, price, and availability. Replace static landing pages with feed-driven product pages. Run daily link and variant checks. The result is fewer wasted clicks and a clearer path to cart. 
2. Payment processing  
   19% said payment processing is the second-largest failure point for retailers. Treat checkout errors as system signals. Track decline codes and 3D secure (3DS) loops. Tune fraud rules to reduce false positives. Align tax and shipping logic with inventory holds so payment retries go through. When payments clear reliably, your media and product page improvements (PDP) have a bigger impact. 
3. Customer care  
   For brands, customer service is the largest post-purchase leak with 22% citing it as their top breakdown. Give service agents one unified view of orders, inventory, and fulfillment. Publish status updates across channels so customers don’t need to ask. Faster resolutions protect margin and earn the next purchase. 
4. Returns and refunds 
   Treat returns as structured feedback. Feed return reason codes back into product copy, images, and targeting to fix fit, spec, and compatibility issues earlier in the funnel. Keep the returns process easy enough to preserve loyalty, but tighten controls where needed.  

Make speed and accuracy inseparable 

According to the index, “Data accuracy and speed can’t be trade-offs. They have to be solved together.” That starts with reducing manual work, checking data as it comes in, keeping prices, inventory, and delivery promises up to date, and stopping bad data before it goes live. 

When performance signals do light up, move quickly: over half of retailers say they respond within 48 hours, while brands are more likely to take three to five business days. Shorten the loop so fixes land while demand is still happening. 

What to scale once the leaks are sealed 

Social commerce leads on conversion, and site experience is close behind. Reach doesn’t matter if the landing page is slow or checkout trips people up. Fix the path first, then spend. 

Customers are shortening the distance from discovery to purchase. The Index’s guidance is simple: fix the biggest leaks first, then scale your spend.  

Download the full report here. To turn the index into an action plan for your team, talk to Rithum today.

The post Your customer journey is leaking revenue. Here’s how to fix it.  appeared first on Rithum.

Summary: Holiday 2025 ecommerce strategy

• Data readiness is uneven. Nearly 3 in 4 retailers and brands say they’re making decisions on incomplete or inaccurate data. Retailers more often act within 48 hours when signals spike, while more brands take 3 to 5 days. 
• Shopper timing has shifted. As covered in our recent webinar, during summer sales season carts were built early and many purchases landed on day 2 to day 4. 
• Where conversion happens is evolving. Social commerce is the top current conversion driver, with site experience close behind. Think live shopping, influencer unboxings, and social-first storytelling that leads directly to purchase. 
• Returns impact profit. 60% of shoppers made at least one return last year. Average processing cost is about $30 per returns. U.S. online returns are projected above $363B; globally, returns account for roughly 17% of sales value. 
• Policy influences purchase. 41% say return policies affect the decision, 88% prioritize free returns, and 47% have stopped buying from a retailer or brand due to policy. 
• Two case notes. Monitoring hourly and leaning back in late improved AOV and conversion by the end of a four-day event. An apparel brand’s mid-event pivot to seasonal assortments, bundles, and cleaner titles delivered a 15% lift over the prior year. 

Shoppers plan early and purchase later

The competing big sales events of July, September, and October have given us an outline of the shape of things to come for holiday season just around the corner. The big themes? Shoppers are planning early and often building carts early then buying late. In our recent webinar, Countdown to holiday 2025: Strategies for growth and agility, experts Kellie Martin, Nistaar Chandhok, and Storm Morgan summed up a new pattern of shopper behavior: “Shoppers were browsing less and buying more deliberately. Cart building happened early, but conversion often didn’t occur until day two or four.” 

The earlier cart building points to the competition of today’s sales season, and the ease of comparison shopping across big sales (especially when shoppers are aided by AI). While early cart building is slowing down the path to purchase, it also gives you longer windows to act on your live sales data—the key is getting the right information quickly, understanding the patterns, and knowing when to change course during a sale (and when to stay steady).  

The 2026 commerce readiness index shows that commerce leaders report uneven data quality and response speed, which matters when promotions land and search behavior shifts.  

Here are some scenarios to help you plan around that pause and move based on what you see as part of your holiday 2025 ecommerce strategy.

Path A: Improve visibility 7 to 10 days before the peak window for your holiday 2025 ecommerce strategy

If data shows you that your discoverability is weak, begin here. The webinar tied early launches to stronger CTR and lower CPC. “You can’t win if you show up late,” Storm said. 

• First, match real searches. Tune product titles and keywords to seasonal queries across the marketplaces and channels you sell through, including your site and social shops. 
• Next, strengthen the product page. Use enhanced product pages with clear bullets and consistent value messaging so comparison shoppers can decide quickly. 
• Then, add early creator content. The webinar highlighted authentic influencer campaigns that show the product in use as a lift when paired with strong product pages. 

Watch CTR, CPC, PDP views, and add to cart. If carts grow but orders land later, go to Path B. If traffic remains thin, stay on Path A and keep improving titles, images, and keywords. 

Path B: Convert day-2 to day-4 buyers without deep discounts 

If carts are building while buyers compare, lean into the timing covered in the webinar. More than a third of shoppers price-check across sites before they commit. 

• First, show value rather than cutting deeper. Bundled offers and loyalty programs lifted average order value in the examples that Storm discussed in the webinar, without the cost of blanket discounts. 
• Next, keep it current. Update titles, keywords, and product page copy to match trending queries and seasonal context during the event. 
• Then, find ready-to-buy-shoppers. AI-driven formats like Google Demand Gen and Performance Max helped when the message was specific to winning new customers. 

Track day-2 and day-4 conversion, AOV, and cart resume rate. If the margin tightens, go to Path C. If traffic softens, return to Path A. 

Path C: Protect margin with value and channel fit 

If revenue grows while profit slips, use the levers shown in the readiness index and webinar. 

• First, tap into pricing agility. Dynamic pricing helped retailers and brands respond to competitors’ moves in real time without broad cuts. 
• Next, set the products and price for each channel. Multichannel shopping is normal. Set assortment and pricing strategy to each channel’s strengths. In the holiday readiness webinar, Storm noted that buyers will pay full price when value is clear, especially for scarce items or well-timed bundles. 
• Then, watch results hour by hour. Rithum saw clients who watched SKUs and profit hour by hour and adjusted as needed. 

If returns start to rise or policy questions distract buyers, move to Path D. 

Path D: Reduce the cost of returns while keeping trust 

Returns are the swing variable in Q4. The 2025 Global Returns & Profit Impact Report quantifies what drives them and what stops them. 

• First, fix issues before purchase. 60% of consumers made at least one return last year. Poor fit is the top driver in apparel at 61%, and about a third of shoppers returned because items did not match descriptions or photos. Clear sizing, accurate copy, and strong images reduce avoidable returns. 
• Next, set clear policies that compete. 41% of consumers say return policies influence purchase, 88% prioritize free returns, and 47% have stopped shopping with a retailer or brand due to policy. If you change terms, make them easy to understand and consistent. 
• Then, plan for common behaviors. Bracketing is a common habit by 36% of global shoppers and over half among shoppers under 35. Two-thirds used third-party drop-off to return at least once in the last 12 months. 51% consider 14 days or less a reasonable window, with higher acceptance of shorter returns windows in some European markets. Understand some of the key levers to lower returns, and lean in.  

Keep an eye on total cost data. The average processing cost is about $30 per return. U.S. online returns are projected above $363B in 2025. 

If operations are steady and you want more demand, go to Path E. 

Path E: Adjust live and capture after-event demand 

If mid-event performance wobbles or you want to extend gains, follow the measured moves shared by Rithum’s experts during the holiday readiness webinar. 

• First, decide with hourly signals. One retailer started slow, held budget, watched hourly, and leaned back in; by the end, AOV and conversion improved, said Storm. 
• Next, pivot toward what is trending. An apparel brand shifted to back-to-school assortments, introduced bundles, and tightened titles and keywords, finishing 15% above the prior year’s Prime event. Per Nistaar: “They were pretty happy with that.” 
• Then, keep campaigns live after the rush. After-event demand is real; in October, we even saw some spending surge higher the day after an event ended than during the first day of the event. Test urgency messaging and retarget saved carts with offers that match the week’s story. 

If visibility still lags, return to Path A. If carts build again and buyers wait until later in the window, go back to Path B. 

Regional notes to localize any path 

If you sell in multiple regions, tune the plan to what shoppers actually do there. In Europe, shoppers compare across Amazon and regional marketplaces like Otto or Allegro, which means titles, keywords, and offers should reference local norms and events. In APAC, Singles Day and other game-like promotions drive activity, so timing and creative should match those mechanics and calendars. In North America, shoppers react strongly to fast delivery promises and a smooth checkout, so make shipping dates and returns information easy to see on the product page. Use these differences to pick which path to start with and which levers to pull first. 

Quick map for retailers and brands 

• If you are not being seen, use Path A. 
• If carts are full and buyers wait, use Path B. 
• If margin is slipping, use Path C. 
• If returns threaten profit, use Path D. 
• If performance is uneven mid-event or you want the tail-end lift, use Path E. 

Start where you are, switch when signals change, and keep each move tied to your data. 

If you’re ready to turn these paths into results, learn how Rithum can help.

Storm Morgan is a Senior Technical Account Manager at Rithum. 

Sources: The 2026 commerce readiness index, Global returns & profit impact report, Countdown to holiday 2025: strategies for growth and agility webinar 

The post What full carts and slower checkouts mean for your holiday 2025 ecommerce strategy appeared first on Rithum.

This quarter is about clarity and faster action. Below is what’s new at Rithum and what’s next for retailers and brands. Items are grouped so teams can jump straight to what they need. 

For retailers: new visibility now, shipping upgrades next 

New Retailer Home Page  

Get a near real-time view across the full order lifecycle, from pick-pack-ship through delivery. Start at a network-level overview, then drill into supplier summaries and order-level details to triage what’s late, at risk, or stalled. It’s built for scale and mirrors how teams actually work: network view to supplier view to order. 

Package Predictor  

Powered by RithumIQ, Package Predictor automatically predicts package weights and dimensions based on real-world shipping behaviors. For retailers using Shipping Optimization, those predictions flow into the label printing process to reduce manual guessing and avoid costly mis-selections. Accuracy stats are forthcoming once broader rollout data is in. 

Coming soon for retailers 

Shipping Optimization Control Center 

Update shipping logic in the platform instead of downloading and re-uploading spreadsheets. Manage supplier defaults, delivery rules, and order conditions in one place. 

Shipping Label Workspace 

See predicted shipments in one view with confidence indicators, then move trusted batches faster while reviewing edge cases. It pairs with Package Predictor so weights and dimensions appear alongside each label.  

Retailer Chatbot 

In pilot now with several of our retailers. You can ask questions like “What were my top-selling SKUs two weeks ago?” and pull platform guidance such as how to run supplier promotions.  

For brands: normalized financials, new marketplaces, and new locales 

Best Buy U.S. 

Best Buy U.S. is live. Reach a large, trusted audience in consumer electronics and home goods. Early adopters can qualify for $0 platform fees until 2026. 

New marketplaces 

• Temu (U.S.): Breakout marketplace with nearly 300 million monthly users globally. 

• Tillys: Specialty retailer for casual apparel, footwear, and accessories rooted in skate and surf culture. 

• BrandAlley U.K.: Curated flash-sale site that’s useful for seasonal sell-through and clearing inventory. 

New locales 

Expansions include Walmart Marketplace Chile, Amazon Ireland, and TikTok Shop in Ireland and Spain. Walmart Chile (coming soon). The marketplace sees about 84 million visits a year and is the first marketplace where we helped launch the Global Item Spec template to speed onboarding. 

Magic Mapper 

Automatically categorizes products across channels with a quick human-in-the-loop review. Powered by RithumIQ, Magic Mapper is designed to save hours of manual effort. 

Coming soon for brands 

Settlement Reports 

We’re centralizing settlement data in Rithum, starting with Walmart and eBay. Export order- and SKU-level detail, including fees, commissions, and taxes, so finance and operations can reconcile payouts in one place. 

Connect with your Rithum team to map next steps. Then read the 2026 commerce readiness index for data on where shoppers are buying, which channels are accelerating, and the levers that protect profit so you can prioritize what to deploy next. 

Curious how it all works? Join us November 12 for the Rithum Pulse: Q4 Product Showcase and get a closer look at the updates built to help your team move faster.

Madison Jarvis is Senior Product Marketer, Retailers, at Rithum. Micah McGuire is Senior Product Marketer, Brands, at Rithum. 

The post Q4 2025 product updates: real-time visibility, shipping control and AI-backed accuracy appeared first on Rithum.

U.S. ecommerce sales will jump 8% this holiday season, while overall retail is predicted to grow 4% during the peak seasonal shopping months. For retailers and brands, that surge raises the stakes: product data must be accurate, sites must perform under pressure, delivery promises must actually deliver, and returns must be seamless (or prevented, if possible). 

The Rithum 2026 commerce readiness index provides a timely view into these challenges. Based on an independent survey of retail and brand executives, it reflects what your peers are prioritizing right now as they prepare for 2026. The index was created to help retailers and brands identify the actions that matter most—and make measurable progress across channels and fulfillment so they’re stable and steady coming into 2026. 

What the survey responses reveal about 2026 for retailers and brands 

Pulling from the responses of commerce executives, the index focuses on what shapes results before and after purchase, the role of data quality in decision-making, how to get the most out of automation, and where the industry is bracing for impact. You’ll see benchmarks and practical plays from peers that will help you guide near-term priorities, including how they’re: 

• Fixing pre-checkout gaps by connecting ads to in-stock SKUs and keeping product pages current 

• Reducing avoidable contacts and returns after purchase 

• Cutting manual work with data standards and automation that speed decisions 

• Protecting margin with a clearer view of cost to serve 

• Implementing AI that delivers results, not just noise 

What breaks the path to purchase 

According to survey respondents, the path to purchase is breaking from a thousand small fractures that add up fast. Shoppers bounce at broken links, out-of-stock products, slow sites, confusing listings, and irrelevant ads. Post-purchase, they churn after poor service, clunky returns, and delayed communication.  

For retailers, the biggest cracks appear before checkout, with the majority pointing to ad-to-product page breakdowns, followed by payment issues. For brands, the pain shows up after the sale, with customer care and returns topping the list.  

Commerce leaders say what’s breaking isn’t just the customer experience, but the systems behind it. Siloed data, manual workflows, and slow response times leave teams reacting after the moment has passed. 

Coming into 2026, retailers and brands are focused on fixing the breaks that lose customers. The index shows where peers are investing in stronger product connections, clearer delivery promises, and smoother service to protect both satisfaction and margin. 

Why better data ends spreadsheet speed 

Many retailers and brands say they’re still stuck at “spreadsheet speed.” Manual work dominates, from vendor analysts pivoting late-order reports in Excel to reconciling conflicting data across systems. These steps slow reaction times and introduce errors that ripple through decisions. 

Nearly three in four executives admit they sometimes act on outdated or inaccurate data. More than one-third say it happens often. That kind of gap leaves strategy shaped by incomplete information rather than facts teams can trust. 

The index points to how retailers and brands are starting to move faster by cutting manual steps so decisions can happen in hours, not days, and so they can rely on standardized data at every level.

Why retailers and brands need this index 

Rithum’s 2026 commerce readiness index reflects what leading retailers and brands say is working before and after purchase, with benchmarks you can use to guide your next steps.  

Download the report to see the full findings. 

The post Use Rithum’s 2026 commerce readiness index to optimize channels and fulfillment today appeared first on Rithum.

A major global brand had an impossible task: onboarding 50,000 SKUs across five marketplaces in less than 48 hours. Manual categorization would have taken weeks.  

With RithumIQ, the AI engine embedded into the Rithum platform, 92% of the work was automated. Tens of thousands of products were accurately classified, with only the edge cases flagged for human review. 

The brand went live on schedule, with clean data and accurate categorization across every channel. 

This kind of story happens every day, thanks to the power of RithumIQ. Built on one of the world’s richest and most comprehensive commerce datasets, RithumIQ processes billions of product updates daily, repairs broken catalog data, shifts ad spend to top-performing SKUs, drives smarter fulfillment decisions in real time, flags pricing and inventory risks before they escalate, and surfaces actionable insights across every stage of the commerce cycle. It’s not an AI buzzword or bolt-on: it’s the foundational intelligence layer proven to turn operational complexity into measurable growth.  

How ‘AI hype’ has hurt commerce 

Commerce has been promised actionable AI for years. But most of what showed up wasn’t built to scale, focused on the right problems, or delivering actual ROI. Many so-called “AI” tools still rely on static rules that can’t adapt to real-world complexity. Dashboards multiply without simplifying decisions, leaving teams buried in low-priority insights. And content generation tools fail to meet marketplace standards, creating more rework than results. The AI promise is big, but the payoff falls short. 

What makes RithumIQ different 

When you use Rithum, you’re using RithumIQ. This means that every part of your product lifecycle, from onboarding and optimization to fulfillment and profitability, has been AI-enhanced with a focus on client outcomes by design. 

One retailer used capabilities powered by RithumIQ to stop a hidden profit drain: SKUs that appeared healthy but were quietly driving high returns and shipping losses. Another used RithumIQ insights to provide their customers with more accurate delivery dates, dynamically adjusting timelines based on warehouse availability, item type, and even day of the week. And those are just two small examples: more happen every day, at every commerce touchpoint. 

These are not empty AI promises, they’re AI results in practice. They’re daily outcomes, delivered at scale for Rithum’s clients. 

Here’s what RithumIQ means for you: 

Clean product data transformation and catalog readiness. RithumIQ automatically detects and fixes broken product data, fills in missing attributes, and recommends optimal category mappings based on billions of data points. This isn’t AI adding to your workload, it’s AI doing the heavy lifting. 

Real-time fulfillment optimization. When warehouses shift or carrier delays hit, RithumIQ helps your fulfillment decisions stay smart and your shipments stay on time. It recommends the best fulfillment strategy for every order and even adapts as conditions change, taking into account: 

• Inventory location 

• Carrier performance and cost 

• Promised delivery dates 

• Item characteristics and delivery region 

Dynamic ad and pricing optimization. RithumIQ reallocates your ad spend in real time, targeting the SKUs and channels delivering the highest conversion and margin lift. It tracks profitability (not just clicks) and refines performance daily. It also identifies: 

• Hidden profit leaks, such as high-return SKUs 

• Pricing strategies that erode margins 

• Supplier and channel ROI patterns over time 

Predictive insights and automated decision support. RithumIQ uses real-time commerce data spanning industries, geographies, and channels to identify demand shifts and predict what will sell where, and when. It can: 

• Anticipate trends before they surface 

• Tailor product content to marketplace audiences 

• Keeps product listings compliant with evolving channel requirements 

And because RithumIQ is embedded in the platform, these insights show up exactly where your teams need them. No separate and disjointed AI experiences. 

AI solution, built for AI-discovery. Your customers are increasingly asking ChatGPT, Perplexity, and other AI tools to give them shopping recommendations, and even buying within those tools directly. If your products aren’t structured in ways that an AI tool recognizes, they simply won’t show up. RithumIQ ensures that when AI-driven shopping assistants suggest products, yours are visible, discoverable, and recommended, by providing: 

• Structured data across SKUs, variants, and fulfillment models 

• Enriched content that’s optimized for machine understanding 

• Faster onboarding into marketplaces and retail media platforms 

RithumIQ is powering the future of commerce intelligence 

From smarter listings to optimized fulfillment to predictive insights, RithumIQ turns massive data into measurable results. And it gets smarter with every transaction. 

That’s the kind of AI that truly works for your team, your customers, and your bottom line. 

Learn more about RithumIQ and what it can do for you. 

Brandon Klein is Director, Product Marketing, at Rithum.

The post RithumIQ gives you AI commerce focused on outcomes, not hype  appeared first on Rithum.

Back-to-school (BTS) shoppers started earlier, spent more cautiously, and favored targeted value over blanket discounts. Back-to-school shopping was a stress test for holiday readiness. Here’s what the data tells us, and how to respond. 

Back-to-school sales: what changed and why it matters 

BTS shopping kicked off early this year, with 67% of K-12 and college shoppers already starting shopping by early July—the biggest early start since NRF began tracking the back to school season. Tariff-related price increases were a big driver, with half saying they moved faster into buy mode to avoid those hits.  

Families planned to spend $858 on average for K-12 (down from 2024), but total K-12 spend prediction ticked up to $39.4B, signaling more shopping despite tighter wallets. This might be because there’s not a ton of choice: if your kid needs new shoes for school, it’s not a discretionary purchase (vs. the holiday season, when gifts are not thought of as the same level of necessity). Online remains the top choice for 55% of consumers, with discount stores getting more traction as shoppers looked for value over loyalty.  

Households are distinguishing “need” vs. “want,” more than ever, expecting uneven price increases as tariffs and cost-of-living costs roll through the commerce world. More deal hunting, more shop-hopping, and more comparison across big events is the norm.  

These patterns—early research, cart building, and channel switching—mirror what we saw over the big summer sales events, and what we told you to prepare beforehand. 

That discretion has also affected buy-now-pay-later (BNPL) usage, which is rising into late summer. Consumers spent $7.8 billion via BNPL in July, up 16.6% yoy, a clear signal for Q4 budgets, according to Adobe Business. 

Key differences in 2025 back-to-school shopping

• Earlier start and longer purchase window. Families chipped away at lists during July events like Prime Day and Walmart Deals, then paused to wait for district lists and late-season apparel decisions, according to NRF.

• Targeted value offers beat blanket discounts. Shoppers respond to relevance (bundles, student perks, durability claims) as much as raw price. Deep, across-the-board cuts aren’t necessary to win the cart.

• Cross-channel comparison is the default. Pricing parity and clean content matter more than ever to prevent abandonment.

What we’re seeing in-market  

Several leading retailers we work with rode out BTS seasonality with no major promotions, and still saw strong demand. For most companies we’re working with who rely on BTS sales, they’ve had little paid push but are still finding that the calendar itself fueled conversion. 

In August, the following categories surged (and cooled): 

• Apparel and footwear stayed resilient as “needs,” helped by off-price and pointed promos, according to NRF. 

• Tech and audio sold well from July through college move-in (laptops, headphones, small appliances), according to Adobe. 

• Backpacks, lunch boxes, and calculators sold fast during July sales and when schools posted supply lists. 

• Shoppers chose store brands and value packs, but mid-season sales slowed and retailers sold fewer items, according to Circana. 

What will this mean for holiday season? 

Everything we’re seeing—value scrutiny, channel switching, event-day triangulation—will define peak shopping season. Here’s what you can expect:  

• Two conversion waves: early research, late-season purchase. Summer event shoppers researched early and converted when the price felt right; BTS saw the same, so expect more coming into the holidays. Plan two waves: early season list building and end season urgency. 

• Tariff news may shift purchase timing. If price-rise rumors accelerate, shoppers pay attention and try to get ahead. If it cools, more will likely look for promotions instead of focus on that anxiety of getting ahead. With the White House’s 90-day extension of the China tariff truce into mid-November 2025, shoppers may be more inclined to wait for big promos. But if the Office of the U.S. Trade Representative’s product exclusions are not extended beyond Aug. 31, some tariff-sensitive purchases could be pulled forward into September, according to KPMG. 

• More cart building, abandonment, and reactivation. Shoppers build their “list” within your cart, they look around for better deals. Track why shoppers are waiting (price watching, incomplete lists, budget staggering) and answer with saved carts, wishlist nudges, and price-drop alerts.  

Want more? Check out our primer on peak season preparedness.  

Meghan Barden is Director, Global Retail Media, Rithum.

The post Back-to-school shopping trends signal earlier, budget-conscious holiday buying appeared first on Rithum.