Bid Landscape Forecasting and Cold Start Problem With Transformers
In Real-Time Bidding, advertisers aim to optimally bid within a limited budget constraint. Effective bidding strategies require bid landscape forecasting to predict the probability distribution of market price for each advertisement auction. This distribution has a complicated form with many peaks....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10418074/ |
| _version_ | 1797299826189139968 |
|---|---|
| author | Daria Yakovleva Sergei Telnov Ilya Makarov Andrey Filchenkov |
| author_facet | Daria Yakovleva Sergei Telnov Ilya Makarov Andrey Filchenkov |
| author_sort | Daria Yakovleva |
| collection | DOAJ |
| description | In Real-Time Bidding, advertisers aim to optimally bid within a limited budget constraint. Effective bidding strategies require bid landscape forecasting to predict the probability distribution of market price for each advertisement auction. This distribution has a complicated form with many peaks. Moreover, all probabilities of bids depend on each other. Most existing solutions mainly focus on learning a parameterized model based on some heuristic assumptions of distribution forms. In this paper, we propose a Transformer model that takes into account dependencies between bids improving the bid landscape forecasting. We also increase the quality of model prediction on the advertisement cold start for the cases of insufficient data. Our experiments on two real-world industrial datasets prove that the proposed model statistically significantly outperforms the state-of-the-art solutions both in terms of ANLP metrics by 8.75% and ROC-AUC by 1.1%. In addition, we show the industrial applicability of our approach. |
| first_indexed | 2024-03-07T22:57:15Z |
| format | Article |
| id | doaj.art-6942afd8bac345edab98db2f8b833ecc |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T22:57:15Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6942afd8bac345edab98db2f8b833ecc2024-02-23T00:00:57ZengIEEEIEEE Access2169-35362024-01-0112191171912710.1109/ACCESS.2024.336049310418074Bid Landscape Forecasting and Cold Start Problem With TransformersDaria Yakovleva0Sergei Telnov1Ilya Makarov2https://orcid.org/0000-0002-3308-8825Andrey Filchenkov3Faculty of Information Technologies and Programming (FITP) ITMO University, Saint Petersburg, RussiaFaculty of Information Technologies and Programming (FITP) ITMO University, Saint Petersburg, RussiaAI Center, National University of Science and Technology (NUST) MISIS, Moscow, RussiaFaculty of Information Technologies and Programming (FITP) ITMO University, Saint Petersburg, RussiaIn Real-Time Bidding, advertisers aim to optimally bid within a limited budget constraint. Effective bidding strategies require bid landscape forecasting to predict the probability distribution of market price for each advertisement auction. This distribution has a complicated form with many peaks. Moreover, all probabilities of bids depend on each other. Most existing solutions mainly focus on learning a parameterized model based on some heuristic assumptions of distribution forms. In this paper, we propose a Transformer model that takes into account dependencies between bids improving the bid landscape forecasting. We also increase the quality of model prediction on the advertisement cold start for the cases of insufficient data. Our experiments on two real-world industrial datasets prove that the proposed model statistically significantly outperforms the state-of-the-art solutions both in terms of ANLP metrics by 8.75% and ROC-AUC by 1.1%. In addition, we show the industrial applicability of our approach.https://ieeexplore.ieee.org/document/10418074/Bid forecastingtransformercold start |
| spellingShingle | Daria Yakovleva Sergei Telnov Ilya Makarov Andrey Filchenkov Bid Landscape Forecasting and Cold Start Problem With Transformers IEEE Access Bid forecasting transformer cold start |
| title | Bid Landscape Forecasting and Cold Start Problem With Transformers |
| title_full | Bid Landscape Forecasting and Cold Start Problem With Transformers |
| title_fullStr | Bid Landscape Forecasting and Cold Start Problem With Transformers |
| title_full_unstemmed | Bid Landscape Forecasting and Cold Start Problem With Transformers |
| title_short | Bid Landscape Forecasting and Cold Start Problem With Transformers |
| title_sort | bid landscape forecasting and cold start problem with transformers |
| topic | Bid forecasting transformer cold start |
| url | https://ieeexplore.ieee.org/document/10418074/ |
| work_keys_str_mv | AT dariayakovleva bidlandscapeforecastingandcoldstartproblemwithtransformers AT sergeitelnov bidlandscapeforecastingandcoldstartproblemwithtransformers AT ilyamakarov bidlandscapeforecastingandcoldstartproblemwithtransformers AT andreyfilchenkov bidlandscapeforecastingandcoldstartproblemwithtransformers |