Abstract:
|
We use a machine-learning-driven approach for designing bundles in a large-scale, cross-category retail setting. We leverage historical purchases and consideration sets determined from clickstream data to generate dense representations (embeddings) of products. We put minimal structure on these embeddings and develop heuristics for complementarity and substitutability among products. Subsequently, we use the heuristics to create multiple bundles for each of 4,500 focal products and test their performance using a field experiment with a large retailer. We use the experimental data to optimize the bundle design policy with offline policy learning. Our optimized policy is robust across product categories, generalizes well to the retailer’s entire assortment, and provides expected improvement of 35% (~$5 per 100 visits) in revenue from bundles over a baseline policy using product co-purchase rates.
|