Optimizing Real-Time Bidding Systems in Programmatic AdvertisingMožina, Marko (Avtor) Demšar, Jure (Mentor) Jakomin, Martin (Komentor) programmatic advertisingreal-time biddingcandidate retrievaltwo-tower modelssampled softmaxmixed negative samplingsampling bias correctiononline A/B testingA demand-side platform has only tens of milliseconds per request to choose the advertisement it will bid with, so the selection runs in stages. The first stage carries much of that weight. A computationally cheap two-tower model scores the large set of eligible candidates and forwards about a hundred of them to heavier processes. Such a model has to tell good candidates from bad ones, yet its training data holds only the advertisements that were chosen in the past. We therefore sample the bad examples from the training batch, and that sampling introduces several kinds of bias into the model. In this thesis we reworked the negative sampling of preselection in a production real-time bidder. We tuned how many negative examples a batch supplies, corrected the bias with a streaming estimate of sampling frequencies, and widened the negatives with uniform draws from the whole set of advertisements. Drawing from two sources calls for a correction that the literature only hints at, so we derived it exactly as a single mixture distribution and showed that it works. We checked every method in a controlled setting on static data and tested it in the live production system. Our sampling methods improved the ranking of candidates decisively, but that improvement did not translate into clear gains in the financial metrics. We attribute the mismatch to the oversized depth of the forwarded shortlist, which masks better ordering before it can reach a business outcome.20262026-09-28 16:50:01Magistrsko delo/naloga188809sl