How Large Graphical Models drive better merchandizing execution
Last update: June 17, 2024
Introduction
Retail continues to be one of the most dominant, resilient, and dynamic industries. Technology has always been central to the space. Over the past couple decades, retailers have leveraged emerging tech to offer a personalized customer experience – in both traditional storefronts and e-commerce sites.
Growing data has always been fundamental to these personalization efforts. For several years, retailers have been using this data in rules-based systems to tailor their services for customers (for example, in product recommendation engines). Rules-based systems are rich with domain expertise. They contain lots of valuable knowledge and IP from the companies deploying them. But they also lack flexibility: Rules-based systems are only as intelligent as their existing logic. They can’t dynamically learn from new information and experiences. When conditions change on the ground, these systems don’t adjust. As a result, they often don’t make the best decisions.
But now, there’s a better option than these systems. Accelerating digital transformation has caused an explosion in data across retail and other industries. This data boom has given birth to modern generative AI technologies. Gen AI can learn in real-time and allows retailers to support personalized experiences in ways that are far more intelligent and responsive than rules-based systems.
Large Graphical Models (LGMs) are the perfect gen AI technology to enable retailers to uncover patterns, predict granular business outcomes, and make good decisions. LGMs leverage tabular, time-series data (which accounts for the majority of data today in retail environments). They can help retailers forecast all sorts of trends across their organization. LGMs are particularly good at hyper-personalization efforts, such as retail merchandizing.
Shoppers are growing accustomed to increasing personalization
Retailers are selling to new generations of buyers that have grown accustomed to more responsiveness and personalization in all aspects of their life. Historically, retailers have only been able to gather data on and market to a general category of customers. For example, back-to-school shoppers or Christmas shoppers. Today, there’s enough granular data available to make Joe Smith his own cohort.
AI and machine learning pilots and POCs are now pervasive in modern retail aiming to build on the investments made in automation, supply chain optimization, mobile shopping apps, customer data platforms, e-commerce platforms, and various analytics solutions that have brought the industry forward. Despite these advancements, many retailers still struggle to deliver hyper-personalized shopping experiences that cater toward individual consumers. This is a particular issue in retail merchandizing.
Merchandizing plays an essential role for modern retailers. Broadly speaking, merchandizing refers to all efforts and strategies to market and sell products to customers once they’ve entered a store (either brick-and-mortar or an e-commerce site). Ultimately, the goal of retail merchandizing is to improve overall sales in this era of hyper-personalization. To put another way, the purpose is to move more and more product (thus maximizing revenue) in the most efficient way.
For traditional retail, merchandizing strategies cover questions like:
- How should I organize products?
- Which items should I put on end caps or on display in the front of the store?
- How much shelf space should I dedicate to a given section?
- How much should we stock of a given product?
- Which items should we promote with in-store signage and coupons?
- How do we ensure that product is available when it’s needed?
Of course,answering these questions is tricky. These are complex problems dependent onmany variables. And what works in one location might fail in another location one mile down the road.
LGMs allow retailers to support hyper-personalization and make merchandizing decisions with confidence
If retailers are able to forecast trends and detect patterns, they can answer the type of questions above, master merchandizing, and ultimately drive greater profits. LGMs were built for doing exactly that.
The Large Graphical Model has proven effective in answering a broad number of forecasting questions about customer demand, supply chain logistics, finance, and other areas. These same outputs can be applied for retail merchandizing. The tech is able to look at diverse data sets and identify patterns and anomalies that uncover buying behavior across categories of product, customer type, store location, etc.
Forecasting the impact of merchandizing efforts on a granular level involves the modelling of tabular, time-series data. This type of data refers to data that is kept in databases and has a specific time associated with it. In a retail setting, this would include Point of Sale data (any information collected during a customer transaction – i.e., SKUs sold, total transaction cost, discounts applied, etc.).
Analyzing this data in detail, along with historical sales data and external data sources like market trends and social media sentiment, unlocks insights that tell retailers how merchandizing strategies are performing. More importantly, it tells them how these strategies will perform in the future against an unlimited number of variables.
Large Graphical Models are designed specifically for tabular, time series data. They capture relationships across many dimensions, making it ideal for forecasting and modeling data of all kinds, and especially effective for tackling highly complex multivariate scenarios like inventory planning, pricing strategies, and product placement that typically characterize merchandizing efforts.
Unlike LLMs, the LGM does not require vast amounts of historical data. In fact, it can deliver precise results even when analyzing small, sparse data sets - a common issue when new products, suppliers, and distribution centers emerge.
LGM technology can simulate various scenarios to test the effectiveness of different merchandizing strategies, all while gaining insights into the business impact of those strategies across key drivers such as cost, inventory, labor, and suppliers.
For instance, retailers can use LGMs to predict outcomes like:
- How will replacing shaving cream products with deodorant products on an endcap impact sales of both and total revenue for the store?
- How long should we plan to stock a new footwear product?
- Which grocery items should we promote via coupons next month?
Case Study: Seasonal retailer deploys Ikigai LGM to improve merchandizing
One major American retailer recently leveraged Ikigai’s patented LGM technology to optimize its merchandizing efforts in a fickle market. The company is a seasonal business that focuses on selling themed costumes and items.
Given their seasonality, they walk a tight line:
- On one hand, the company needs to avoid overstocking and ending up with excess inventory at the end of each season (which means unsold goods and wasted CAPEX).
- At the same time, they also don’t want to run out of inventory early (which means they missed out on sales).
The company has used Ikigai to strike this balance and guide its retail merchandizing efforts for the past three years – both nationally and on a local level.
Ikigai has helped the business answer questions like:
- Which themed items should I stock this season?
- How many should we stock of each SKU overall?
- How well will one SKU sell at a specific location?
- How well will this accessory sell with this costume?
- How can we avoid cannibalizing sales in cities where we have multiple stores?
- How will new themed items perform?
With Ikigai’s ability to uncover patterns and make predictions based on granular, tabular, time-series data, the company was able to remove the guesswork from their merchandizing decisions. So far, they’ve found that Ikigai’s forecasts are 70% more accurate than the proprietary forecasting they had previously relied on. As a result, the company has been able to lower inventory costs, boost sales, and ultimately grow profit.
Use Ikigai generative AI to guide your retail business
Retail is a cutthroat industry where margins are always razor thin. In this context, precision makes the difference between growth and bankruptcy. The rules-based personalization efforts of the past aren’t enough today – customers instead expect hyper-personalization. LGMs equip retailers with the insights to tailor shopping experiences at an unprecedented level. This can be seen in their use guiding modern merchandizing efforts.
Visit here to learn more about how you can leverage Ikigai LGMs for various retail use cases.
To learn more about the Ikigai platform, visit here.
Download PDF
To download the eBook as a PDF, click here.