Application of conformal prediction interval estimations to market makers’ net positions

Wojciech Wisniewski, David Lindsay, Sian Lindsay
Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications, PMLR 128:285-301, 2020.

Abstract

In this study we focus on the application of Conformal Prediction (CP) interval estimations to provide financial Market Makers (MMs) with some “meaningful” forecasts relating to their future short-term position in a given financial market. The idea is that using these market position forecasts, MMs can deploy proactive risk management strategies with a given degree of confidence. We make use of a novel financial time series dataset that comprises the net positions of a given MM over a three year period for trades pertaining to the top-traded Foreign Exchange (FX) symbols. This dataset – \nolinebreak{NetPositionTimeSeries} – is noisy and complex. The net positions within it are generated from the trades of tens of thousands of clients trading in different directions (buy or sell) and over many different time horizons. We approached the problem of predicting future net position not as one that required an accurate point estimate as this is impossible. Rather we sought to gain a meaningful range of possible position bounds which would nonetheless be invaluable. In this study we tested a range of predictive Machine Learning (ML) techniques. We compared the CP framework to benchmark methods like moving average (MA) and quantile regression (QR). We demonstrate how application of the CP framework gives well calibrated region bounds on the MM net position forecasts.

Cite this Paper

BibTeX
@InProceedings{pmlr-v128-wisniewski20a, title = {Application of conformal prediction interval estimations to market makers’ net positions}, author = {Wisniewski, Wojciech and Lindsay, David and Lindsay, Sian}, booktitle = {Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications}, pages = {285--301}, year = {2020}, editor = {Gammerman, Alexander and Vovk, Vladimir and Luo, Zhiyuan and Smirnov, Evgueni and Cherubin, Giovanni}, volume = {128}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v128/wisniewski20a/wisniewski20a.pdf}, url = {https://proceedings.mlr.press/v128/wisniewski20a.html}, abstract = { In this study we focus on the application of Conformal Prediction (CP) interval estimations to provide financial Market Makers (MMs) with some “meaningful” forecasts relating to their future short-term position in a given financial market. The idea is that using these market position forecasts, MMs can deploy proactive risk management strategies with a given degree of confidence. We make use of a novel financial time series dataset that comprises the net positions of a given MM over a three year period for trades pertaining to the top-traded Foreign Exchange (FX) symbols. This dataset – \nolinebreak{NetPositionTimeSeries} – is noisy and complex. The net positions within it are generated from the trades of tens of thousands of clients trading in different directions (buy or sell) and over many different time horizons. We approached the problem of predicting future net position not as one that required an accurate point estimate as this is impossible. Rather we sought to gain a meaningful range of possible position bounds which would nonetheless be invaluable. In this study we tested a range of predictive Machine Learning (ML) techniques. We compared the CP framework to benchmark methods like moving average (MA) and quantile regression (QR). We demonstrate how application of the CP framework gives well calibrated region bounds on the MM net position forecasts.} }
Endnote
%0 Conference Paper %T Application of conformal prediction interval estimations to market makers’ net positions %A Wojciech Wisniewski %A David Lindsay %A Sian Lindsay %B Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications %C Proceedings of Machine Learning Research %D 2020 %E Alexander Gammerman %E Vladimir Vovk %E Zhiyuan Luo %E Evgueni Smirnov %E Giovanni Cherubin %F pmlr-v128-wisniewski20a %I PMLR %P 285--301 %U https://proceedings.mlr.press/v128/wisniewski20a.html %V 128 %X In this study we focus on the application of Conformal Prediction (CP) interval estimations to provide financial Market Makers (MMs) with some “meaningful” forecasts relating to their future short-term position in a given financial market. The idea is that using these market position forecasts, MMs can deploy proactive risk management strategies with a given degree of confidence. We make use of a novel financial time series dataset that comprises the net positions of a given MM over a three year period for trades pertaining to the top-traded Foreign Exchange (FX) symbols. This dataset – \nolinebreak{NetPositionTimeSeries} – is noisy and complex. The net positions within it are generated from the trades of tens of thousands of clients trading in different directions (buy or sell) and over many different time horizons. We approached the problem of predicting future net position not as one that required an accurate point estimate as this is impossible. Rather we sought to gain a meaningful range of possible position bounds which would nonetheless be invaluable. In this study we tested a range of predictive Machine Learning (ML) techniques. We compared the CP framework to benchmark methods like moving average (MA) and quantile regression (QR). We demonstrate how application of the CP framework gives well calibrated region bounds on the MM net position forecasts.
APA
Wisniewski, W., Lindsay, D. & Lindsay, S.. (2020). Application of conformal prediction interval estimations to market makers’ net positions. Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications, in Proceedings of Machine Learning Research 128:285-301 Available from https://proceedings.mlr.press/v128/wisniewski20a.html.

Related Material