Case Study: Retail
Lack of a data science approach leads to high cost markdown waves, usage of Excel formulae based process is less accurate and inconsistent and manual process limits the number of markdown waves leading to increased cost.
Created a modernized/automated tool on a cloud platform by using advanced statistical models and machine learning algorithms to predict optimum Markdowns. The tool is capable of integrating with multiple data sources and can be easily and remotely accessible. This helped the client to plan better markdown strategies backed by empirical data from the ML models.
Savings in Markdown Cost with better planning based on the accurate lift predictions. Reduced inventory disposal fee and provided big rewards by improving sell-through rates. Higher revenues and consequently increased net margin apart from productivity gains and a better negotiation on Markdown Contracts with retailers.