Cross-Merchandising Techniques

Machine learning beats traditional forecasting methods in multi series forecasting. In one of the latest M forecasting competitions, the aim was to advance what we know about time series forecasting methods and strategies. Competitors had to forecast 40k+ time series representing sales for the largest retail company in the world by revenue: Walmart. These are the main findings: ▶️ Performance of ML Methods: Machine learning (ML) models demonstrate superior accuracy compared to simple statistical methods. Hybrid approaches that combine ML techniques with statistical functionalities often yield effective results. Advanced ML methods, such as LightGBM and deep learning techniques, have shown significant forecasting potential. ▶️ Value of Combining Forecasts: Combining forecasts from various methods enhances accuracy. Even simple, equal-weighted combinations of models can outperform more complex approaches, reaffirming the effectiveness of ensemble strategies. ▶️ Cross-Learning Benefits: Utilizing cross-learning from correlated, hierarchical data improves forecasting accuracy. In short, one model to forecast thousands of time series. This approach allows for more efficient training and reduces computational costs, making it a valuable strategy. ▶️ Differences in Performance: Winning methods often outperform traditional benchmarks significantly. However, many teams may not surpass the performance of simpler methods, indicating that straightforward approaches can still be effective. Impact of External Adjustments: Incorporating external adjustments (ie, data based insight) can enhance forecast accuracy. ▶️ Importance of Cross-Validation Strategies: Effective cross-validation (CV) strategies are crucial for accurately assessing forecasting methods. Many teams fail to select the best forecasts due to inadequate CV methods. Utilizing extensive validation techniques can ensure robustness. ▶️ Role of Exogenous Variables: Including exogenous/explanatory variables significantly improves forecasting accuracy. Additional data such as promotions and price changes can lead to substantial improvements over models that rely solely on historical data. Overall, these findings emphasize the effectiveness of ML methods, the value of combining forecasts, and the importance of incorporating external factors and robust validation strategies in forecasting. If you haven’t already, try using machine learning models to forecast your future challenge 🙂 Read the article 👉 https://buff.ly/3O95gQp

UK retail is in the middle of a stress test, where a clear divide is opening up between winners pulling ahead and those losing ground. After speaking to Retail Week’s Hugh Radojev for his trading analysis piece, a few points stand out. We’ve been operating in a state of ‘permacrisis’ for years now – from Covid and supply chain chaos to inflation and geopolitical shocks. But disruption doesn’t explain why some retailers are struggling and others such as Marks and Spencer, Next and Tesco continue to grow market share. An execution gap has emerged. Our Retail Economics research with Barclays Corporate Banking, based on a survey of more than 100 senior retail executives, shows a widening divide – with three in five leaders saying the gap between high and low performers is growing. Complexity has crept in where: ·      Many retailers misread post-Covid demand as structural growth ·      Inflation masked weak trading ·      Digital touch points ballooned, creating operational drag and margin pressure ·      Leadership teams misaligned and slower to adapt   Retail today has become far more technical, where instinct combines with data, analytics and cross-functional execution. Those pulling ahead combine old-school merchant discipline with targeted investment, to build relevance and agility and better respond to adversity, including: ➡️       Relentless focus on pricing, stock discipline and cash ➡️       Investing in customer-led growth – personalisation, new channels, partnerships ➡️       Using technology to enhance decision-making The leaders now are often those with the agility to reprice, reroute and rebalance stock faster than everyone else to secure market share. ____________________________________ ⤴ Follow me for weekly retail, consumer and economic insights. ____________________________________

I've analyzed 10,000+ sales calls and discovered something shocking… Elite closers NEVER discount when asked, "Can I get a better price?" While most reps panic and immediately cave, the top 1% have a completely different playbook 👇 Instead, they have a systematic approach that PRESERVES margins while CLOSING more deals. When you're quick to discount, you communicate TWO things that DESTROY trust: 1️⃣ "YOU CAN'T TRUST ME". They'll think: "Why didn't they give me the best price initially?" This makes them suspicious of everything else you've said. 2️⃣ "MY PRODUCT ISN'T WORTH IT". You're telling them you don't believe in your own value. If YOU don't believe it, why should THEY? Before using any strategy, run the objection through my H.E.A.R.T. framework: - H-ear them: "Cari, I appreciate the ask." - E-laborate: "Help me understand why you're asking?" - A-side: “Aside from the pricing, is anything else giving you pause?" - R-eclarify value: "What did you like most about our solution?" - T-ransition: Now use one of these 5 strategies... ➡️STRATEGY #1. THE REDUCTION CLOSE "Let's review everything in your package and remove what's 'nice-to-have' versus 'must-have.' Then we'll recalculate." You're NOT giving a discount. You're reducing what they're buying. Most prospects realize they want everything and end up paying full price anyway. ➡️STRATEGY #2. THE SUBSTITUTE CLOSE "I know we discussed Option X. Another option is Y, it does things 1, 2, and 3 but doesn't have 4, 5, or 6. However, it's $XXX less." Again, NO discount. Just a lower-priced alternative that creates value comparison. When they see what they lose, they often stick with the premium solution. ➡️STRATEGY #3. THE UPSELL VALUE GIVE "I can't discount, but I CAN include Premium Support for 30 days. Normally reserved for our highest tier and costs 30% more." The magic? They often upgrade after experiencing the premium feature! This is my personal favorite with the highest conversion. ➡️STRATEGY #4. THE 3 OPTION CLOSE Present good/better/best options BEFORE the price objection happens. When they ask for a discount, guide them to the lower option. This makes THEM decide between features vs. price. Instead of YOU deciding between discount or no deal. ➡️STRATEGY #5. FLEXIBLE PAYMENT TERMS Instead of cutting price, adjust WHEN and HOW they pay: → Half now, half in 30 days → Payments over 3 months → Net-30 instead of Net-15 One Fortune 500 client increased close rates 32% with this approach alone. ➡️THE LAST RESORT: GIVE TO GET If you absolutely MUST discount, NEVER give without getting something in return: "I can do 10% off if we add 5 more licenses." OR "I can do 10% off if you introduce me to 5 other business owners who could use our solution." You're conditioning how you do business AND maximizing value. — Hey sales pros, want to handle objections better? Go here: https://lnkd.in/g-uJ7ECX

I walked into Miniso just to browse, but a tiny design detail caught my attention I reached for a perfume tester, expecting to spray it on my wrist. But there was no push-button. Just an open nozzle, forcing me to bring it close and take a sniff. Observations: 🛍️ Smart Product Placement: Perfumes were neatly arranged in visually appealing color blocks, making selection feel intuitive. 👃 Tester Trick: The tester bottles had no push-button sprays! Instead, customers had to directly sniff the nozzle—reducing impulse spraying by passersby and ensuring serious buyers engage more deeply. 👉 Behavioral Science in Action: 📌 Commitment Bias: If you take the effort to pick up and sniff, you're more likely to consider buying. 📌Scarcity Effect: No free-flowing spray means the product feels more 'exclusive.' 📌Decision Fatigue Reduction: Minimal distractions, clear choices, and a structured layout make buying easier. Retailers are getting smarter—it's not just about WHAT they sell but HOW they sell it. Have you noticed any clever behavioral tactics in stores lately? #BehavioralScience #RetailPsychology #ConsumerBehavior #MarketingStrategy #BrandExperience 

Forecasting is a common application of data science, and it's crucial for businesses to manage their inventory, especially those with perishable items effectively. In a recent tech blog, the data science team from Afresh shared an innovative approach to accurately predict demand, incorporating non-traditional factors such as in-store promotions. Promotions are common in grocery stores, helping customers discover and purchase discounted items. However, these promotions can significantly alter customer behavior, making traditional forecasting methods less reliable. Traditional models struggle to incorporate these factors, often leading to higher prediction errors. To address this challenge, Afresh’s data science team developed a deep learning forecasting model that integrates various features, including promotional activities tied to specific products. The model's performance was evaluated using a normalized quantile loss metric, showing an 80% reduction in loss during promotion periods. This example highlights the superior performance of this solution and showcases the power of deep learning in solving a critical issue for the grocery industry. #machinelearning #datascience #forecasting #inventory #prediction – – –  Check out the "Snacks Weekly on Data Science" podcast and subscribe, where I explain in more detail the concepts discussed in this and future posts:    -- Spotify: https://lnkd.in/gKgaMvbh   -- Apple Podcast: https://lnkd.in/gj6aPBBY    -- Youtube: https://lnkd.in/gcwPeBmR https://lnkd.in/gWRgTJ2Q 

Are store openings making a comeback, or is the future still digital? After years of predictions that physical stores were finished, 2025 is telling a different story. According to CBRE, store openings in the US actually outpaced closures in 2024, with net growth led by value retailers, specialty food, and experience-focused concepts. In the GCC, new mall expansions and pop-up activations remain on the rise, with UAE retail sales projected to reach $63.6 billion by 2025 (Dubai Chamber of Commerce). Why the shift? Consumers want more than transactions. From Gen Z to Boomers, shoppers are seeking experiences, whether it’s in-store events, live demonstrations, or interactive tech. Gen Z is surprisingly pro-physical: A 2024 NRF study found that 81% of Gen Zers prefer to shop in stores for fashion and beauty, valuing instant gratification, social interaction, and immersive brand storytelling. Millennials still drive online spending but now use stores for pick-up, returns, and brand discovery. Older generations favor physical for trust and service, but even they are using retailer apps for loyalty and convenience. E-commerce sales, on the other hand, continue double-digit growth, especially in categories like electronics, home, and health. “Hybrid” shopping, think click-and-collect, QR code browsing, and virtual store assistants, is becoming the new norm. Is this retail renaissance a sustainable shift or simply a response to post-pandemic fatigue and novelty? As customer expectations evolve, the future may belong to brands that blend the best of both worlds. How has your own shopping behavior changed? Are you visiting stores more, and what’s drawing you in? For retailers, what’s actually working to get people off their phones and into physical space? Share your thoughts, stories, or predictions for the future of retail. #retailtrends #consumerinsight #shopping #storeexperience #futureofretail

Ever wonder why some e-commerce brands always seem to have the right products in stock, while others struggle with overstock or empty shelves? It all comes down to demand forecasting—and in 2025, it’s getting an AI-powered upgrade. ● From guesswork to precision Traditional forecasting relies on historical sales data. AI-driven tools now go beyond that, integrating real-time factors like weather, local events, and even social media trends. The result? Forecasts with 90%+ accuracy instead of the usual 50%. ● GenAI: the next step Generative AI takes it further by analyzing unstructured data (customer reviews, trends, emerging demand signals) and answering questions in plain language. No more complex spreadsheets—just instant insights for better inventory planning. ● AI tools leading the way: ✔ Simporter – AI-powered forecasting that integrates multiple data sources to predict sales trends. ✔ Forts – uses AI for demand and supply planning, ensuring optimized inventory. ✔ ThirdEye Data – AI-driven forecasting that factors in seasonality and customer behavior. ✔ Swap – AI-based logistics platform that enhances inventory management. ✔ Nosto – AI-driven personalization that recommends the right products at the right time. ● Why this matters for #ecommerce? ✔️ Avoid stockouts that frustrate customers ✔️ Reduce excess inventory and free up cash ✔️ Adapt quickly to market shifts How are you managing demand forecasting in your store? #shopify

𝗬𝗼𝘂 𝘁𝘂𝗻𝗲 𝘆𝗼𝘂𝗿 𝗺𝗼𝗱𝗲𝗹 𝗽𝗲𝗿𝗳𝗲𝗰𝘁𝗹𝘆 – 𝗯𝘂𝘁 𝗶𝘁 𝗰𝗼𝗹𝗹𝗮𝗽𝘀𝗲𝘀 𝘄𝗵𝗲𝗻 𝗕𝗹𝗮𝗰𝗸 𝗙𝗿𝗶𝗱𝗮𝘆 𝗵𝗶𝘁𝘀.🧙♂️ “Demand forecasting” sounds like one problem. But it’s at least two – and they need different solutions. For example: 1. Daily demand forecasting for the complete product range. Thousands of items, every day, across all locations. We often use algorithms like gradient boosting, deep learning – and yes, even “standard” regressions. The challenge: include everything – price, seasonality, trends, stock levels – and keep it stable without overfitting. The risk? These models tend to learn the average. Peaks often get smoothed out or missed entirely. 2. Then there’s peak event forecasting for holidays, promos, or major events. Totally different game. We need models built to target the spikes – that recognize events and adjust dynamically. They might not be the best at modeling the average though! But they’re better at capturing outliers and extremes. Sometimes lightweight time series models do better here. Or quantile regressions combined with external signals. The goal: anticipate sales behavior when it breaks the usual patterns. My word of caution? Assuming the same model can handle both. This is a great reminder to check early what your business actually needs forecasting for. #ALDITechfluencer #DataScience #DemandForecasting

I learned a tangible lesson sometime back about selling, and this works across all sectors: retail, software products, and more. TLDR: Design your experience so that the next favorable action is always visible, because if you don’t surface it, you can’t sell it. I will use a coffee shop as an analogy to explain it. If a customer walks in and buys a coffee, they clearly have intent to purchase, but if no one mentions that bread, a pastry, or a combo deal is available, that opportunity disappears silently. Not because the customer rejected it, but because it was never surfaced. Take a common scenario: > A customer orders a coffee. >> They might also want a pastry. Unless someone says, "would you want a pastry with that? It’s a popular combo," they’ll likely stick to just the coffee. Same with a meat pie. Suggest a drink or a side, and the basket grows. > Say nothing, and the moment passes. This is where upselling and cross-selling are often misunderstood. It’s not about pushing more products. It’s about making relevant options visible at the right moment. Customers usually operate on a default path: I’ll just get what I came for. A well-timed suggestion does two things: 1. Expands their consideration set 2. Increases the total value of the transaction with minimal friction There’s a catch: if you pitch everything, you dilute impact. If you pitch nothing, you leave revenue on the table. The leverage is in precision: suggest what naturally complements the current purchase. Keep it to one or two high-probability add-ons, and frame it as helpful, not transactional. > Do you want anything else? - is weak. >> Do you want a pastry with your coffee? It’s a popular combo.” converts. For product managers and sales teams, the takeaway is simple: Design your experience so that the next best action is always visible, because if you don’t surface it, you can’t sell it.

Have you ever heard of Terminal Marketing? It's a marketing strategy you've never heard of but definitely used before. Discover the power of this marketing concept and unlock new possibilities for your strategies. Let's dive in! 👇 Terminal Marketing refers to a strategy focused on the final stage of the customer journey—the point at which a decision to purchase is made. It emphasizes the importance of the last 'terminal' interaction before purchase, leveraging it to influence the customer's choice. When is Terminal Marketing effective? It shines in high-competition markets where differentiation is minimal, and the decision boils down to the last moment of interaction. Think retail environments, online checkouts, or service subscriptions where the final nudge is crucial. On the other hand, Terminal Marketing can backfire if it is overly aggressive or poorly executed, leading to decision fatigue or negative brand perception. It's less effective in scenarios where purchases are driven by long-term relationships or detailed research. Strategy-wise, personalization is key. Tailoring the final interaction to the customer's previous engagements can significantly increase conversion rates. A common example would be dynamic retargeting ads or product recommendations based on past sessions. Scarcity and urgency are classic tactics that still work wonders. A "Limited Time Offer" or "Only a Few Left" message at the checkout can push customers over the line. However, ensure these tactics are genuine to avoid eroding trust. Social proof at the point of decision can be a game-changer. Including testimonials, reviews, or user-generated content near the purchase point can alleviate last-minute doubts and showcase the value and satisfaction of your product or service. Another effective strategy is to simplify the buying process. Reducing the steps to purchase, offering multiple payment options, and providing clear, concise information can prevent drop-offs. Amazon’s "One-Click" purchase is a prime example of this in action. Real-world example: Booking(dot)com uses Terminal Marketing effectively by displaying messages about how many people are looking at a room, limited availability, and recent bookings. This creates a sense of urgency and encourages immediate booking. Another example is Spotify's offering a free trial of its premium service when users are frustrated with ads. This timely offer, precisely when the user experiences a pain point, makes the premium service more appealing. Of course, this pain point is also created by design. To sum up, Terminal Marketing is about capturing the customer at the pivotal moment of decision-making. By understanding your audience and applying strategies like personalization, urgency, and simplification, you can boost conversions significantly.