search

shinleylee / Arbitrary_Distribution_Modeling

Arbitrary Distribution Modeling with Censorship in Real Time Bidding Advertising for KDD'22
13 stars 2 forks source link

How to create bidding price #1

Open franktseng0718 opened 1 year ago

franktseng0718 commented 1 year ago

I'd like to reproduce your research result in your paper, but I wonder how you fake the bidding price to simulate the winning and losing samples, or can you provide the code of your preprocessing？

AllardJM commented 1 year ago

Also interested in this!

AllardJM commented 1 year ago

@franktseng0718 did you ever find an example of this methodology? It sounds like its a "standard" way to evaluate offline

shinleylee commented 1 year ago

Aye! I‘d like to introduce the paper

Wu W C H, Yeh M Y, Chen M S. Predicting winning price in real time bidding with censored data[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2015: 1305-1314.

to you guys where it elaborated the data preparation in section 4.1. Also, this method was applied in

Wu W, Yeh M Y, Chen M S. Deep censored learning of the winning price in the real time bidding[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018: 2526-2535.

Ren K, Qin J, Zheng L, et al. Deep landscape forecasting for real-time bidding advertising[C]//Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019: 363-372.

just name a few. You can easily find the description in their 4.1 sections.

Hope this helps. @franktseng0718 @AllardJM

AllardJM commented 1 year ago

@shinleylee Do you think this data prep only works with second price auctions? If so, have you seen anything dealing with first price?