Driven by the disruptive events of the past year, retailers have had to fundamentally reassess how they do business, resulting in pushing digital transformation forward at previously unknown speeds. The importance of technology to the industry has also been accentuated, thereby accelerating digitization driving retailers to adopt technologies across the business – customer experience, operations, people, and finance with a two-fold focus on attracting and retaining customers and optimizing costs.
Algorithmic retailing gets a push as it encompasses the combined power of advanced analytics and artificial intelligence to transform retailing as we know it. Retailers have been using various advanced analytics technologies and are beginning to leverage machine learning algorithms, smart data discovery, context-aware computing, and deep learning technologies.
We’re witnessing the process of retail decision-making as well as the mindset of retailers experiencing a drastic change. On the back of this trend, algorithmic merchandising is experiencing a spike in adoption for retailers want to build business resilience while being customer-centric in their approach.
According to Gartner’s Hype Cycle for Retail Technologies, 2021, “Algorithmic retailing connects big data to results, navigating a journey from descriptive to prescriptive analytics. This journey includes the identiﬁcation of data sources, use of automation and advanced analytics, and application of algorithms and artiﬁcial intelligence that will lead to highly repeatable and tenable business processes. It is the use of mathematical algorithms, data discovery, advanced analytic capabilities, and AI, combined with automation, to drive effective decision making.”
Merchandising forms a key part of Algorithmic Retailing and will enable retailers to attain higher sales and margins. The technology seamlessly supports complex analytics that customer-centricity requires, enabling smarter decisions at any level of the retail organization.
Let’s dwell on how algorithmic merchandising can have a huge impact during the different stages of seasonal or cyclical retail businesses.
The Pre-Season Stage
During this crucial planning stage, retailers perform a lot of demand forecasting which consequently drives the allocation, production, and sales plans. During this phase, analytics systems are used to forecast how products will fare in the market. Retailers have never completely relied on or trusted the data-driven demand forecasting model as they know that there are multiple other variables that affect demand. Even if analytical tools are used, a lot of gut and experience-based micro-decisions are made to generate demand forecasts. For instance, in fashion retail, new products are designed every season based on several factors like style, fabric, color, cuts, patterns, fit, finish, and texture that eventually influence shopping decisions.
In such a scenario, AI and machine-powered analytics systems offer greater control over the use of these variables in modeling demand and therefore promise higher accuracy on the demand forecast. AI-augmented analytics takes into consideration the business context, real-time data, external influencers like weather, promotions, social media reviews, the performance of similar products, and a lot more to forecast demand.
Accurate demand forecasting in turn determines how well the inventory gets managed, how the pricing decisions get made, what kind of customer-engagement strategies get implemented, and much more.
The In-Season Stage
During this phase, the retailer’s focus is to execute according to the sales plan and generate maximum profits from the inventory. Inability to closely monitor how products are selling across the stores and controlling their inventory movement to match the plan typically results in out-of-stock situations or excess stocks that must be heavily marked down and cleared off at the end of the season.
With thousands of products and styles moving across hundreds of stores, businesses today rely on algorithmic processes. These can detect patterns and bring to light the under-performing products that need a temporary price reduction tactic early in the season to maximize their revenue during the rest of the season.
These algorithmic anomalies also uncover other opportunities in the business, like changing store merchandising or running behaviorally targeted campaigns to lift sales. In this phase, retailers can leverage algorithmic retailing for inventory optimization, price recommendation, assortment tuning, new product sales optimization, customer-centric offer recommendations, personalized promotions, and a lot more. All these results in optimized sales and profits.
The End of Season Stage
After the season is over, products that have not sold well despite in-season optimization efforts have to be marked down in a specific promotional/clearance window. AI and machine learning techniques are useful in processing answers to questions like – “What percentage of markdown price is ideal for each product to clear off its inventory?” Or “Which products have the most chances of a sale in which store locations?”
Algorithmic markdown analytics continuously optimizes markdown price for the highest return on inventory in each store cluster and store location. It analyzes which products need to be discounted, what should be the amount of the discount, the price elasticity, competition from other retailers, ongoing promotions, other marketing techniques, shelf placements, and so on.
AI-augmented algorithms can build several decision trees at the same time on a variety of sub-groups and then combine them all to present a predictive solution. They can also interface with pricing systems to automatically (or through a workflow) implement recommended price changes across the store network, thereby making it easier to implement the pricing decisions.
Algonomy’s Algorithmic Merchandising Solutions
Realizing the disruptive power of these technologies, Algonomy has been focusing heavily on AI and machine learning techniques to automate data management, algorithm processing, and insight generation in order to improve analytics consumption across the retail organization. We apply these technologies in retail merchandising applications to automatically sense the merchandising user’s decision context, machine-generate insights, make AI-augmented recommendations, and execute the decisions.
Our AI-powered analytics platform also offers a conversational analytics interface that allows users to talk to the system in the natural language. Users can not only run descriptive analytics uses cases, but also complex predictive and prescriptive ones. For these reasons, Algonomy’s AI-powered retail and merchandising solutions have found special mention in categories including, “AI in Retail”, “Algorithmic Retailing” and “Retail assortment management applications”, in Gartner’s Hype Cycle for Retail Technologies, 2021.
Write to us to understand how our customer-centric Merchandising Analytics Solution leverages the power of AI to offer superior business outcomes.