Recommendation Algorithms and E-commerce

Abstract

E-commerce and digital marketing are becoming data-intensive areas. Deep learning can have a huge impact in these areas since high benefits can be achieved with marginal gains in accuracy. For instance, marginal improvements in the click-through rate (CTR) prediction or conversion ratio (CR) of users interacting with web content, either on PC or on mobile devices, may result in millions of dollars of savings in customer acquisition. However, this problem is becoming more complex as the user journey before product acquisition can be complex, with many contact points before purchase. Complex model attribution (the discovery of the trajectory of the user before buying a product) is thus necessary to correctly allocate the ad budget.