{"type":"ScholarlyArticle","title":"Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance","authors":[{"name":"Di Chen","slug":"di-chen","given":"Di","family":"Chen","affiliation":"Cornell University"},{"name":"Yada Zhu","slug":"yada-zhu","given":"Yada","family":"Zhu","affiliation":"IBM T. J. Watson Research Center"},{"name":"Xiaodong Cui","slug":"xiaodong-cui","given":"Xiaodong","family":"Cui","affiliation":"IBM T. J. Watson Research Center"},{"name":"Carla Gomes","slug":"carla-gomes","given":"Carla","family":"Gomes","affiliation":"Cornell University"}],"abstract":"Real-world applications often involve domain-specific and task-based performance objectives that are not captured by the standard machine learning losses, but are critical for decision making. A key challenge for direct integration of more meaningful domain and task-based evaluation criteria into an end-to-end gradient-based training process is the fact that often such performance objectives are not necessarily differentiable and may even require additional decision-making optimization processing. We propose the Task-Oriented Prediction Network (TOPNet), an end-to-end learning scheme that automatically integrates task-based evaluation criteria into the learning process via a learnable surrogate loss function, which directly guides the model towards the task-based goal. A major benefit of the proposed TOPNet learning scheme lies in its capability of automatically integrating non-differentiable evaluation criteria, which makes it particularly suitable for diversified and customized task-based evaluation criteria in real-world tasks. We validate the performance of TOPNet on two real-world financial prediction tasks, revenue surprise forecasting and credit risk modeling. The experimental results demonstrate that TOPNet significantly outperforms both traditional modeling with standard losses and modeling with hand-crafted heuristic differentiable surrogate losses.","doi":"10.24963/ijcai.2020/617","url":"https://ijcai.org/proceedings/2020/617","pdf":"https://ijcai.org/proceedings/2020/0617.pdf","markdown":"https://ijcai.org/proceedings/2020/617.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/617","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Special Track on AI in FinTech","track":"Special Track on AI in FinTech","number":617,"pages":{"first":4476,"last":4482},"keywords":["Foundation for AI in FinTech: General","Foundation for AI in FinTech: Computational intelligence for FinTech"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24414/file_24414.m3u8","length_sec":723,"provider":"hls"}],"references":[{"position":1,"raw":"[Bengio, 1997] Yoshua Bengio. Using a financial training criterion rather than a prediction criterion. International Journal of Neural Systems, 8(04):433-443, 1997.","title":"Using a financial training criterion rather than a prediction criterion","authors":"Yoshua Bengio","year":"1997","venue":"International Journal of Neural Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Donti et al., 2017] Priya Donti, Brandon Amos, and J Zico Kolter. Task-based end-to-end model learning in stochastic optimization. In Advances in Neural Information Process- ing Systems, pages 5484-5494, 2017.","title":"Task-based end-to-end model learning in stochastic optimization","authors":"Priya Donti, Brandon Amos, J Zico Kolter","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Doumpos et al., 2019] M. Doumpos, C. Lemonakis, D. Niklis, and C. Zopounidis. Introduction to credit risk modeling and assessment. In In: Analytical Techniques in the Assessment of Credit Risk. EURO Advanced Tutorials on Operational Research, pages 1-21. Springer, Cham, 2019.","title":"Introduction to credit risk modeling and assessment","authors":"M Doumpos, C Lemonakis, D Niklis, C Zopounidis","year":"2019","venue":"Analytical Techniques in the Assessment of Credit Risk. EURO Advanced Tutorials on Operational Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Elmachtoub and Grigas, 2017] Adam N Elmachtoub and Paul Grigas. Smart\" predict, then optimize\". arXiv preprint arXiv:1710.08005, 2017.","title":"Smart\" predict, then optimize","authors":"N Adam, Paul Elmachtoub, Grigas","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jegadeesh and Livnat, 2006] Narasimhan Jegadeesh and Joshua Livnat. Revenue surprises and stock returns. Journal of Accounting and Economics, 41, 2006.","title":"Revenue surprises and stock returns","authors":"Narasimhan Jegadeesh, Joshua Livnat","year":"2006","venue":"Journal of Accounting and Economics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kao et al., 2009] Yi-hao Kao, Benjamin V Roy, and Xiang Yan. Directed regression. In Advances in Neural Informa- tion Processing Systems, pages 889-897, 2009.","title":"Directed regression","authors":"Yi-Hao Kao, Benjamin V Roy, Xiang Yan","year":"2009","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kingma and Ba, 2014] Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"Diederik Kingma, Jimmy Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Perrault et al., 2019] Andrew Perrault, Bryan Wilder, Eric Ewing, Aditya Mate, Bistra Dilkina, and Milind Tambe. Decision-focused learning of adversary behavior in secu- rity games. arXiv preprint arXiv:1903.00958, 2019.","title":"Decision-focused learning of adversary behavior in security games","authors":"Andrew Perrault, Bryan Wilder, Eric Ewing, Aditya Mate, Bistra Dilkina, Milind Tambe","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Prado, 2018] Marcos Lopez de Prado. Advances in Finan- cial Machine Learning. Wiley, 2018.","title":"Advances in Financial Machine Learning","authors":"Marcos Lopez De Prado","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Riemer et al., 2016] Matthew Riemer, Aditya Vempaty, Flavio P. Calmon, Fenno F. Heath, III, Richard Hull, and Elham Khabiri. Correcting forecasts with multifac- tor neural attention. In Proceedings of the 33rd Inter- national Conference on International Conference on Ma- chine Learning -Volume 48, ICML'16, pages 3010-3019. JMLR.org, 2016.","title":"Correcting forecasts with multifactor neural attention","authors":"Matthew Riemer, Aditya Vempaty, P Flavio, Fenno F Calmon, Iii Heath, Richard Hull, Elham Khabiri","year":"2016","venue":"Proceedings of the 33rd International Conference on International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Wilder et al., 2019a] Bryan Wilder, Bistra Dilkina, and Milind Tambe. Melding the data-decisions pipeline: Decision-focused learning for combinatorial optimization. In Proceedings of the AAAI Conference on Artificial Intel- ligence, volume 33, pages 1658-1665, 2019.","title":"Melding the data-decisions pipeline: Decision-focused learning for combinatorial optimization","authors":"Wilder","year":"2019","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Wilder et al., 2019b] Bryan Wilder, Eric Ewing, Bistra Dilkina, and Milind Tambe. End to end learning and op- timization on graphs. arXiv preprint arXiv:1905.13732, 2019.","title":"End to end learning and optimization on graphs","authors":"Wilder","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Yang et al., 2017] Hongxia Yang, Yada Zhu, and Jingrui He. Local algorithm for user action prediction towards display ads. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '17, pages 2091-2099, New York, NY, USA, 2017. ACM.","title":"Local algorithm for user action prediction towards display ads","authors":"Hongxia Yang, Yada Zhu, Jingrui He","year":"2017","venue":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '17","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}