Specialist Experts for Prediction with Side Information. / Kalnishkan, Yury; Adamskiy, Dmitry; Chernov, Alexey; Scarfe, Tim.

2015 IEEE International Conference on Data Mining Workshop (ICDMW). IEEE, 2016. p. 1470-1477.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Standard

Specialist Experts for Prediction with Side Information. / Kalnishkan, Yury; Adamskiy, Dmitry; Chernov, Alexey; Scarfe, Tim.

2015 IEEE International Conference on Data Mining Workshop (ICDMW). IEEE, 2016. p. 1470-1477.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Kalnishkan, Y, Adamskiy, D, Chernov, A & Scarfe, T 2016, Specialist Experts for Prediction with Side Information. in 2015 IEEE International Conference on Data Mining Workshop (ICDMW). IEEE, pp. 1470-1477. https://doi.org/10.1109/ICDMW.2015.161

APA

Kalnishkan, Y., Adamskiy, D., Chernov, A., & Scarfe, T. (2016). Specialist Experts for Prediction with Side Information. In 2015 IEEE International Conference on Data Mining Workshop (ICDMW) (pp. 1470-1477). IEEE. https://doi.org/10.1109/ICDMW.2015.161

Vancouver

Kalnishkan Y, Adamskiy D, Chernov A, Scarfe T. Specialist Experts for Prediction with Side Information. In 2015 IEEE International Conference on Data Mining Workshop (ICDMW). IEEE. 2016. p. 1470-1477 https://doi.org/10.1109/ICDMW.2015.161

Author

Kalnishkan, Yury ; Adamskiy, Dmitry ; Chernov, Alexey ; Scarfe, Tim. / Specialist Experts for Prediction with Side Information. 2015 IEEE International Conference on Data Mining Workshop (ICDMW). IEEE, 2016. pp. 1470-1477

BibTeX

@inproceedings{6b307d4c6c55482ba3295dd2f34c3cab,
title = "Specialist Experts for Prediction with Side Information",
abstract = "The paper proposes the vicinities merging algorithm for prediction with side information. The algorithm is based on specialist experts techniques. We use vicinities in the side information domain to identify relevant past examples, apply standard learning techniques to them, and then use prediction with expert advice tools to merge those predictions. Guarantees from the theory of prediction with expert advice ensure that helpful vicinities are selected dynamically. The algorithm automatically converges on the right vicinities from an initial broad selection. We apply the resulting algorithms to two problems, prediction of implied volatility of options and prediction of students' performance at tests. On the problem of predicting implied volatility, the algorithm consistently outperforms naive competitors and a highly-tuned proprietary method used in the industry. When applied to the students' performance, the algorithm never falls behind the baseline and outperforms it when the side information is beneficial.",
author = "Yury Kalnishkan and Dmitry Adamskiy and Alexey Chernov and Tim Scarfe",
year = "2016",
doi = "10.1109/ICDMW.2015.161",
language = "English",
isbn = "978-1-4673-8492-6",
pages = "1470--1477",
booktitle = "2015 IEEE International Conference on Data Mining Workshop (ICDMW)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Specialist Experts for Prediction with Side Information

AU - Kalnishkan, Yury

AU - Adamskiy, Dmitry

AU - Chernov, Alexey

AU - Scarfe, Tim

PY - 2016

Y1 - 2016

N2 - The paper proposes the vicinities merging algorithm for prediction with side information. The algorithm is based on specialist experts techniques. We use vicinities in the side information domain to identify relevant past examples, apply standard learning techniques to them, and then use prediction with expert advice tools to merge those predictions. Guarantees from the theory of prediction with expert advice ensure that helpful vicinities are selected dynamically. The algorithm automatically converges on the right vicinities from an initial broad selection. We apply the resulting algorithms to two problems, prediction of implied volatility of options and prediction of students' performance at tests. On the problem of predicting implied volatility, the algorithm consistently outperforms naive competitors and a highly-tuned proprietary method used in the industry. When applied to the students' performance, the algorithm never falls behind the baseline and outperforms it when the side information is beneficial.

AB - The paper proposes the vicinities merging algorithm for prediction with side information. The algorithm is based on specialist experts techniques. We use vicinities in the side information domain to identify relevant past examples, apply standard learning techniques to them, and then use prediction with expert advice tools to merge those predictions. Guarantees from the theory of prediction with expert advice ensure that helpful vicinities are selected dynamically. The algorithm automatically converges on the right vicinities from an initial broad selection. We apply the resulting algorithms to two problems, prediction of implied volatility of options and prediction of students' performance at tests. On the problem of predicting implied volatility, the algorithm consistently outperforms naive competitors and a highly-tuned proprietary method used in the industry. When applied to the students' performance, the algorithm never falls behind the baseline and outperforms it when the side information is beneficial.

U2 - 10.1109/ICDMW.2015.161

DO - 10.1109/ICDMW.2015.161

M3 - Conference contribution

SN - 978-1-4673-8492-6

SP - 1470

EP - 1477

BT - 2015 IEEE International Conference on Data Mining Workshop (ICDMW)

PB - IEEE

ER -