Shopping Cart Analysis Techniques

Crowning a New Term: “Iceberg Metrics” 🧊 ✨ I’m calling it: Iceberg Metrics represent KPIs that only reveal the tip of what’s really happening below the surface. Metrics like abandoned carts seem simple but often mask much more—checkout friction, hidden costs, trust issues, and more. To truly understand and optimize, we need to dig deeper. Here’s how to dive into the “iceberg” of abandoned cart rates: 1. Establish Baseline Metrics: Start by gathering data on current abandoned cart rates, session times, and bounce rates using heat maps and session recordings to see where users drop off. 2. Segment the Audience: Analyze users by behavior (first-time vs. repeat visitors, mobile vs. desktop) and traffic source (organic, paid, email). 3. Experiment Hypotheses: Develop hypotheses for abandonment reasons—shipping costs, checkout friction, distractions, or lack of trust signals—and test them. 4. Run A/B Tests: Test variations like simplifying the checkout process, showing shipping costs earlier, adding trust badges, or retargeting abandoned cart emails. 5. Use Heat Maps & Session Recordings: Examine user behavior in real time. Look for confusion or hesitation, where users hover, and whether they engage with key information. 6. Contextualize Results: Analyze how changes impact overall user flow. Did simplifying checkout help, or did other metrics like bounce rate increase? 7. Ecosystem Approach: Examine how tweaks affect the full journey—from product discovery to checkout—balancing short-term improvements with long-term goals like lifetime value. 8. Iterate: Refine solutions based on experiment findings and continuously optimize the customer journey. This one’s mine, folks! #IcebergMetrics #OwnIt #DataDriven #EcommerceOptimization #NewMetricAlert Cheers, Your cross-legged CAC and CLV buddy 🤗

$47 BILLION in carts abandoned last year. (Not because of the high price or shipping cost.) Because of unanswered questions at 11:47 PM. After analyzing thousands of checkout sessions at Amenexia.ai, I discovered something brutal: Every abandoned cart has a silent question behind it. Right there, credit card half-typed, they're wondering: "What if it doesn't fit?" "Is this site even legit?" "Can I return this easily?" "How long will this really take?" Your return policy is buried in small print. Your FAQ is 3 clicks away. Your chat is offline. Customers are not leaving because they don't want your product. Customers are leaving because their doubt grew faster than desire. Here's what actually works: Instead of optimizing for more traffic, optimize for that final second of hesitation. Put answers where anxiety lives: → "2-3 days delivery to [their city]" at checkout → "Free returns, no questions" next to the buy button → "347 people bought this safely today" by payment fields → "Still unsure? Here's what others asked..." as they hover One client added a simple line: "Yes, this works with [product they viewed earlier]" Conversions jumped 23%. Because at 11:47 PM, your customer doesn't need a salesperson. They need to trust you. Stop optimizing traffic. Start optimizing doubt. The sale isn't lost to competitors. It's lost to questions you never knew they had. PS. When do you usually shop online - morning or late night?

How Walmart Uses AI to Recommend Kitchen Tools When You Buy Milk Ever wonder why Amazon suggests a milk frother when you add milk to your cart? The challenge is harder than it looks—how do you bridge the gap between routine grocery purchases and discovering useful general merchandise? 👉 The Challenge Traditional recommendation systems excel at suggesting similar items (milk → cheese) but struggle with cross-category discovery (milk → milk frother). The problem becomes even trickier when customers have 20+ items in their grocery cart—which products should drive recommendations, and how do you rank them intelligently? 👉 Walmart's Dual Approach Researchers at Walmart Global Tech developed a two-stage system that combines the best of both worlds: Stage 1: Smart Candidate Generation - Historical co-purchase analysis identifies proven item pairs - Large Language Models (LLMs) generate contextual suggestions that go beyond purchase history - Example: For eggs, the LLM suggests egg poachers, timers, and specialized pans—items that enhance the egg experience but might not appear in traditional data Stage 2: Real-Time Cart Context Ranking - A transformer-based neural network analyzes the entire cart contents - Uses cross-attention to understand how potential recommendations relate to all cart items simultaneously - Considers customer persona, platform, and sequential shopping behavior 👉 The Results The system delivered impressive improvements: - 36% increase in add-to-cart rates for LLM-generated recommendations - 27% lift in ranking quality (NDCG@4) when using full cart context - 4.7x more unique recommendation coverage compared to traditional methods 👉 Why This Matters This research tackles a fundamental e-commerce challenge: helping customers discover products they didn't know they needed. By combining AI reasoning with behavioral data, the system creates those "aha moments" where a grocery run becomes an opportunity for useful discovery. The approach shows how modern AI can enhance rather than replace traditional recommendation methods, creating more engaging shopping experiences while driving meaningful business results. Paper by Akshay Kekuda, Murali Mohana Krishna Dandu, Rimita Lahiri, Shiqin Cai, Sinduja Subramaniam, Evren Korpeoglu, and Kannan Achan from Walmart Global Tech.

The smartest sellers are studying buying behavior. Search Query Performance (SQP) gets all the attention, and for good reason. It tells you what’s bringing people in. But it doesn’t tell you who they are or what else they buy once they’re in. That’s where Market Basket Analysis comes in, and most brands are overlooking it. What sellers assume: That success on Amazon is just about targeting better search terms, ranking higher, and converting faster. What’s actually happening: Amazon is quietly telling you who your buyer is through what they add to their cart with your product. Market Basket Analysis (available through Brand Analytics) shows which ASINs are frequently purchased alongside yours. It’s not just an accessory report. It’s an audience signal. Think about what you can learn: • What types of products your customer also buys • What categories they shop in and where you’re missing presence • What brands you’re most commonly paired with (or competing against) • How your product fits into a larger use case or solution This isn’t just helpful for cross-selling. It reframes how you define the role your product plays in the customer’s life. And when you understand that, your entire strategy shifts: → Better bundles → Smarter A+ and brand store design → More relevant ad targeting → More accurate assumptions about lifetime value Amazon is not just a search engine. It’s a marketplace of people with routines, context, and intent. Market Basket Analysis helps you stop guessing. It connects the dots between your product and your real audience, not just the keywords they typed. If you’re still optimizing in isolation, you’re missing what’s actually moving in the cart. Because what good are perfect keywords for the wrong customer? So to start using this report, check out the video and see how to find it on your account #AmazonSellers #BrandRegistry #MarketBasketAnalysis #AmazonData

🛒 You can’t track purchase intent by tracking ATCs. 𝟭. “𝗔𝗧𝗖” 𝗷𝘂𝘀𝘁 𝗺𝗲𝗮𝗻𝘀 “𝘀𝗮𝘃𝗲 𝗳𝗼𝗿 𝗹𝗮𝘁𝗲𝗿”. It’s a placeholder, not a promise. 𝟮. 𝗣𝗲𝗼𝗽𝗹𝗲 𝘂𝘀𝗲 𝘁𝗵𝗲 𝗰𝗮𝗿𝘁 𝗹𝗶𝗸𝗲 𝗣𝗶𝗻𝘁𝗲𝗿𝗲𝘀𝘁. It’s a tool for collecting, not committing. 𝟯. 𝗧𝗵𝗲 𝗰𝗮𝗿𝘁 𝗵𝗲𝗹𝗽𝘀 𝗼𝗿𝗴𝗮𝗻𝗶𝘇𝗲, 𝗻𝗼𝘁 𝗽𝗿𝗶𝗼𝗿𝗶𝘁𝗶𝘇𝗲. It helps them compare…not decide. 𝟰. 𝗡𝗼 𝗳𝗿𝗶𝗰𝘁𝗶𝗼𝗻 = 𝗻𝗼 𝗰𝗼𝗺𝗺𝗶𝘁𝗺𝗲𝗻𝘁. Clicking isn’t buying. It costs nothing to put something in an online cart. 𝟱. 𝗔𝗧𝗖𝘀 𝗺𝗲𝗮𝘀𝘂𝗿𝗲 𝗰𝘂𝗿𝗶𝗼𝘀𝗶𝘁𝘆 𝗼𝗻𝗹𝘆. Interest? Yes. Intent? Not even close. If you really want to track intent, do this instead: ✅ 1. Track high-friction actions Not all clicks are equal. Look for: • Initiate Checkout • Payment Info Entered • Return Visitor → PDP → Checkout • Product added after reading reviews These behaviors show someone is moving past curiosity into commitment. ✅ 2. Analyze sequence, not single actions One ATC means nothing. But: 𝘈𝘛𝘊 → 𝘝𝘪𝘦𝘸 𝘴𝘩𝘪𝘱𝘱𝘪𝘯𝘨 𝘱𝘰𝘭𝘪𝘤𝘺 → 𝘈𝘥𝘥 𝘢𝘥𝘥𝘳𝘦𝘴𝘴? Now we’re talkin’ intent. Watch the flow, not the isolated click. ✅ 3. Measure time spent on key friction points If someone lingers on: • Product comparisons • Return policy pages • Size charts or FAQs They’re mentally preparing to convert. They’re not just browsing at that point, they’re weighing the trade-offs. ✅ 4. Look for repeat product interactions If someone revisits the same PDP 2–3 times in a week, that’s real consideration. Bonus points if they come back from an email or ad reminder. ✅ 5. Use survey overlays or post-exit polls Ask simple, direct questions like: “Are you planning to buy today?” “What’s stopping you from checking out?” Self-reported “logic” + behavioral data = gold. 𝘛𝘓𝘋𝘙: 𝘈𝘛𝘊 𝘪𝘴 𝘪𝘯𝘵𝘦𝘳𝘦𝘴𝘵-𝘭𝘦𝘷𝘦𝘭 𝘣𝘦𝘩𝘢𝘷𝘪𝘰𝘳 𝘰𝘯𝘭𝘺. 𝘐𝘵 𝘸𝘰𝘯’𝘵 𝘵𝘦𝘭𝘭 𝘺𝘰𝘶 𝘪𝘧 𝘺𝘰𝘶𝘳 𝘤𝘶𝘴𝘵𝘰𝘮𝘦𝘳𝘴 𝘢𝘳𝘦 𝘵𝘳𝘶𝘭𝘺 𝘳𝘦𝘢𝘥𝘺 𝘵𝘰 𝘣𝘶𝘺. 𝘛𝘰 𝘵𝘳𝘶𝘭𝘺 𝘵𝘳𝘢𝘤𝘬 𝘪𝘯𝘵𝘦𝘯𝘵, 𝘮𝘰𝘯𝘪𝘵𝘰𝘳 𝘤𝘩𝘦𝘤𝘬𝘰𝘶𝘵 𝘮𝘰𝘮𝘦𝘯𝘵𝘶𝘮.

𝗜𝗱𝗲𝗮 #𝟭𝟰: 𝗢𝗽𝘁𝗶𝗺𝗶𝘀𝗶𝗻𝗴 𝗧𝗵𝗲 𝗗𝗶𝗴𝗶𝘁𝗮𝗹 𝗙𝘂𝗻𝗻𝗲𝗹 A simple funnel (enter site, view product, add to cart, checkout) is no longer sufficient to drive actionable insight. The proliferation of devices, browsers, marketing sources, entry pages and customer journeys requires both a more detailed funnel and more forensic approach to analysis.  What’s needed now is a more systematic way to connect customer journeys to business action. I propose a three-step approach: 𝟭. 𝗗𝗲𝗳𝗶𝗻𝗲 𝗧𝗵𝗲 𝗙𝘂𝗻𝗻𝗲𝗹.  Break the journey down into core steps, micro steps and causal factors [see example] • 𝗖𝗼𝗿𝗲 𝘀𝘁𝗲𝗽𝘀: Referring source/link/code → Landing page → Product page → Add to cart → Checkout • 𝗠𝗶𝗰𝗿𝗼-𝘀𝘁𝗲𝗽𝘀: Interactions within steps (e.g., form fields, size selection, product choices, payment stages) • 𝗖𝗮𝘂𝘀𝗮𝗹 𝗳𝗮𝗰𝘁𝗼𝗿𝘀: Measurable elements that influence conversion—such as price, availability, content and UX.    𝟮. 𝗦𝗹𝗶𝗰𝗶𝗻𝗴 𝗱𝗶𝗺𝗲𝗻𝘀𝗶𝗼𝗻𝘀.  Identify the key dimensions for analysis which should include all attributes that are potentially actionable • 𝗛𝗼𝘄: Technology used (device, browser) • 𝗪𝗵𝗲𝗻: Timing factors (signup date, day of week, time of day) • 𝗪𝗵𝗲𝗿𝗲: Source of traffic (geo, channel, referrer, keyword, landing page) • 𝗪𝗵𝗼: Customer characteristics: new vs. existing visitor, new vs. existing customer, cohort of first browse / purchase, demographics     𝟯. 𝗔𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝗮𝗹 𝗟𝗲𝗻𝘀𝗲𝘀.  Take a systematic approach to highlight what’s driving the funnel and where to optimise: • 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲:  Overall funnel, step-to-step transition rates, funnel x dimensions • 𝗗𝗶𝗮𝗴𝗻𝗼𝘀𝗶𝘀:  Mix effect analysis (decomposes changes into mix shifts vs absolute changes), causal factors • 𝗜𝗻𝘀𝗶𝗴𝗵𝘁:  Outliers (high/low performers across dimensions), causal failures (stock-outs, pricing errors, promo issues). Taking a systematic approach is fundamental to driving long term value and solving root causes rather than symptoms.  Some example insights: • 𝗕𝗿𝗼𝘄𝘀𝗲𝗿 𝗳𝗮𝗶𝗹𝘂𝗿𝗲.  A service business who found that their website didn’t work on older browsers which represented 5% of customers, but 20% of their profit.   • 𝗣𝗿𝗶𝗰𝗲 𝗰𝗼𝗺𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲𝗻𝗲𝘀𝘀.  A general merchandise retailer discovered that the conversion rate issues were driven by price competitiveness issues on their highest viewed products  • 𝗔𝘃𝗮𝗶𝗹𝗮𝗯𝗶𝗹𝗶𝘁𝘆.  A retailer who discovered their bounce rate was being driven by traffic from paid social landing onto sold out products • 𝗦𝗲𝗰𝗿𝗲𝘁𝗮𝗿𝗶𝗲𝘀.  A hotel chain who discovered a visitor segment with a very high conversion rate characterised by frequent bookings, browsing during office hours on a desktop computer using Internet Explorer.  They turned out to be secretaries.  Funnels must evolve from being seen as a purely digital concern and understood as a lens into overall business performance.

Most businesses panic when they see their average order value (AOV) drop 25%. They then… - Slash prices - Rush promotions - Question their premium products But smart retailers know better — they investigate patterns first. Here are a few to get you started: 1. Sales data Your 6-month trends reveal the first signs of change: - Did price changes affect order value? - Which products are selling more or less? - What's the pattern in shopping cart composition? - What does purchase frequency tell us? - What's hiding in abandoned carts? - Are premium products getting abandoned? 🧩 Let’s say you see premium items getting abandoned at checkout repeatedly. Looking deeper, you might find a specific price threshold — leading to an opportunity for strategic bundling. 2. Website behavior Tools like CrazyEgg, LuckyOrange, Hotjar, and FullStory show complete interaction patterns: - Most visited pages - Heat map patterns - Premium product engagement 🧩 Are customers spending time on review sections but leaving? You might need stronger social proof and not necessarily lower prices. 3. Customer voices Data tells half the story, and your customers tell the other half. Direct fact-finding reveals… - Customer sentiments on new premium products - Views on popular vs. unpopular items - Feedback on existing products Social media conversations add another layer of insight. 🧩 Suppose your focus groups reveal confusion about premium features. This could signal you need better education — not different products. 4. Competitive landscape A comprehensive look at your market reveals if competitors… - Launched promotions that coincided with the change - Introduced new products during your AOV drop - Brought innovative solutions to the market - Lowered their existing product prices 🧩 Did you notice your AOV drop right when a competitor introduced similar products at lower prices? This is a direct connection between market changes and your sales patterns. 5. Long-term trends Customer surveys help you identify shifts in popularity before they hurt your bottom line. 🧩 If they show customers gradually losing interest in a once-popular product category… You’ve spotted a trend that explains your dropping order value (and suggests you should act accordingly). 💡 Remember this: Numbers don't drop without reason. Patterns don't form by accident. Solutions don't come from guessing. Understanding your customers' behavior is the difference between reacting and leading.

I watched a $20M DTC brand bleed cash for 18 months—because it ignored cart economics. Here’s What Most Brands Miss: ✅ Unit economics ≠ SKU economics. ✅ Customers buy carts, not products—analyze the whole basket. Cart economics is the profit lever most brands overlook. The Real Math Behind Profitable Growth: 1. Start at Cart Level → Average Unit Retail × Units Per Transaction = Gross Retail → Gross Retail = your effective pre-discount pricing power. 2. Factor in Discounts and Returns → Subtract average discount rate (by coupon). → Subtract average return rate (critical, especially in apparel). 3. Add Shipping Collected → Most brands ignore this. → Cash collected at checkout counts. It matters. 4. Calculate True Average Order Value → Gross Retail - Discounts - Returns + Shipping = True AOV → (Way more accurate than Shopify’s AOV.) 5. Layer in Cost Structure → COGS + Fulfillment + Payment Processing = Total Cost of Delivery. 6. Get to Gross Margin → True AOV – Total Cost of Delivery = Gross Profit → Gross Profit ÷ True AOV = Gross Margin % 7. Factor in CAC → Total Marketing Spend ÷ New Customers = Blended CAC. → Gross Profit – CAC = Contribution Margin (CM3). Where Good Brands Go Broke: → Ignoring return rates = fake margins. → Relying on platform AOV = fake pricing assumptions. → Undercharging on shipping = giving away profit for free. → Not segmenting first-time vs. returning orders = broken growth math. The 4 Levers That Actually Move Profit: 1. Increase Units Per Transaction → Bundling, cross-sells, upsells = fastest way to double profit. 2. Control Discount Rates → Over-discounting isn’t demand generation. It’s lazy marketing. → Build demand through creative, not coupons. 3. Improve COGS via Product Mix → Sell more high-margin products. Don’t just negotiate harder. 4. Drop Blended CAC through Creative Volume → Media buying efficiency is capped by creative strategy. → High-volume creative testing isn’t optional anymore. Small % improvements across these = exponential bottom-line gains. Bottom Line: Scale Margin, Not Just Revenue: You don't scale eCommerce brands by scaling spend. You scale them by scaling contribution margin. ✅ Fix cart economics first. ✅ Segment first-time vs. returning customer unit economics. ✅ Pull the biggest profit levers—units per cart, discounting, product mix, CAC. ✅ Treat creative volume as a financial strategy, not a marketing one. If you can't make money on a $100 cart, you won't make money with a $1M ad budget either. Agree, disagree, or see it a different way? Would love to hear your take! ♻️ Like, comment, and repost to help out another marketer. Hit follow for more.

In one of my previous company, As an analyst. I have worked on market basket analysis and It played as a strong pillar in designing promotional campaigns and bundle offers. Lets deep dive into it. 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗠𝗮𝗿𝗸𝗲𝘁 𝗕𝗮𝘀𝗸𝗲𝘁 𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀? 𝘐𝘮𝘱𝘰𝘳𝘵𝘢𝘯𝘵 𝘧𝘰𝘳 𝘢 𝘥𝘢𝘵𝘢 𝘢𝘯𝘢𝘭𝘺𝘴𝘵s 𝘵𝘰 𝘪𝘯𝘤𝘳𝘦𝘢𝘴𝘦 𝘵𝘩𝘦𝘪𝘳 𝘣𝘶𝘴𝘪𝘯𝘦𝘴𝘴 𝘒𝘯𝘰𝘸𝘭𝘦𝘥𝘨𝘦 By leveraging the powerful concepts of 𝘀𝘂𝗽𝗽𝗼𝗿𝘁, 𝗹𝗶𝗳𝘁, 𝗮𝗻𝗱 𝗰𝗼𝗻𝗳𝗶𝗱𝗲𝗻𝗰𝗲, I 𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀 𝗢𝘃𝗲𝗿𝘃𝗶𝗲𝘄: Using 𝗗𝗔𝗫 𝗳𝗼𝗿𝗺𝘂𝗹𝗮𝘀, I conducted an extensive analysis of grocery items data, focusing on the relationships between products in customers baskets. The three key concepts that drove my analysis were support, lift, and confidence. Support measures the frequency of item combinations, lift quantifies the strength of association between items, confidence determines the likelihood of one item being purchased given the presence of another. 𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 𝗮𝗻𝗱 𝗕𝗲𝗻𝗲𝗳𝗶𝘁𝘀: Grocery basket analysis has gained immense popularity across various industries due to its versatile applications and numerous benefits. Here's how companies are leveraging this technique to their advantage: 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿 𝗕𝗲𝗵𝗮𝘃𝗶𝗼𝗿 𝗜𝗻𝘀𝗶𝗴𝗵𝘁𝘀: By examining support values, we can identify frequently occurring item combinations. This knowledge empowers companies to understand customers' purchasing habits better, leading to personalized marketing strategies and optimized product placements. Uncovering hidden relationships among items allows retailers to cross-sell and upsell effectively, improving customer satisfaction and revenue. 𝗣𝗿𝗼𝗺𝗼𝘁𝗶𝗼𝗻𝗮𝗹 𝗖𝗮𝗺𝗽𝗮𝗶𝗴𝗻𝘀: With confidence values, companies can design targeted promotions and recommendations. By offering complementary products based on the presence of others in a customer's basket, businesses can increase sales and encourage impulse purchases. This personalized marketing approach enhances customer engagement and drives revenue growth. 𝗔𝘀𝘀𝗼𝗿𝘁𝗺𝗲𝗻𝘁 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Grocery basket analysis allows companies to tailor their product assortments to customers' preferences. By analyzing support and lift values, retailers can identify items that are frequently purchased together, enabling them to curate well-aligned product categories. This optimization helps maximize sales, reduce waste, and improve overall customer experience. 𝐄-𝐜𝐨𝐦𝐦𝐞𝐫𝐜𝐞 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦𝐬: Online platforms are leveraging grocery basket analysis to provide personalized recommendations. By suggesting items based on customers' purchasing patterns and related products, these platforms have seen substantial improvements in conversion rates and customer loyalty. #GroceryBasketAnalysis #MarketBasketAnalysis #AffinityAnalysis #DataMining #AssociationRules #CrossSelling #DataAnalytics #RetailInsight