- Our Price Recommendations Engine uses a holistic approach. It leverages multi-stage optimization, and it factors in multiple business considerations at each stage.
- Our solution uses over 5 years of historical transactions to derive a price-demand relationship for each SKU; using curve fitting and deep learning techniques. The solution accounts for factors such as: competitors’ pricing, cross/intra-category impact, market growth, and consumer price index. It also provides ‘what-if’ scenario capabilities. Using the demand price relationships derived, the optimal price, i.e, the price at which the margin can be maximized without losing revenue, is recommended.
- The recommendations engine offers flexibilities for scenario analysis, which significantly helps in a collaborative decision making process, and it allows for category manager interventions. Ultimately, it leverages a self-learning approach to continuously improve modelling accuracy.
- Adopting the data-driven pricing strategy helped the retailer meet its profitability goals. The analysis was based on the category and the geography; the improved pricing strategy had no adverse impact on the revenue.
- Implementing “better” buying decisions increased profitability because category managers were able to use scenario analysis to assess the impact of vendor offers and associated price reductions.
A multi-category retailer wanted to identify the “right” price points for each SKU in a given market. The goal was to achieve higher margins without having an adverse impact on revenue. Operating in over 7 countries and with over 100,000 SKUs, the retailer needed a data-driven pricing strategy that quickly adapted to changing business scenarios.