Waktu Indonesia Belanja or WIB is a monthly shopping festival that Tokopedia organizes offering many discounts and flash sales across the site. Always on the lookout for greater successes, Tokopedia’s Browse Ads team took up the challenge to face the WIB event.
We show ad recommendations on many browse pages across the Tokopedia platform. But providing the best in class experience to a high number of concurrent users is a challenging task. We decided to do multiple improvements and optimizations in our system to be able to serve that amount of traffic!
A look at the improvements we achieved:
I work in a team that designs algorithms for recommending ads on Tokopedia. We measure the performance of our algorithms daily. During one such performance measurement exercise, we came across a prominent problem in our system — we noticed that the same ads were being recommended to our buyers repeatedly, despite their bad performance. How did we find this? Well, the count of impressions for ads remained almost the same every day which means we were showing almost the same ads to the users on their every visit.