Big Data And PAC Learning In The Presence Of Noise: Implications For Financial Risk Management

Chinthalapati, V.L.R., Mitra, S. and Serguieva, A. 2019. Big Data And PAC Learning In The Presence Of Noise: Implications For Financial Risk Management. International Journal of Artificial Intelligence. 17 (1), pp. 34-56.

TitleBig Data And PAC Learning In The Presence Of Noise: Implications For Financial Risk Management
TypeJournal article
AuthorsChinthalapati, V.L.R., Mitra, S. and Serguieva, A.
Abstract

High accuracy forecasts are essential to financial risk management, where machine learning algorithms are frequently employed. We derive a new theoretical bound on the sample complexity for PAC learning in the presence of noise, and does not require specification of the hypothesis set |H|. Consequently, we demonstrate that for realistic financial applications (where |H|is typically infinite) that big data is necessary, contrary to prior theoretical conclusions. Secondly, we show that noise (which is a non-trivial component of big data) has a dominating impact on the data size required for PAC learning. Consequently, contrary to current big data trends, we argue that high quality data is more important than large volumes of data. Thirdly, we demonstrate that the level of algorithmic sophistication (specifically the Vapnik Chervonenkis dimension) needs to be traded-off against data requirements to ensure optimal algorithmic performance. Finally, our new Theorem can be applied to a wider range of machine learning algorithms, as it does not impose finite |H| requirements. This paper will be of interest to researchers and industry specialists who are interested in machine learning in financial
applications.

KeywordsBig Data
Risk Management
Noisy Data
Machine Learning
VC Dimension
Sample Complexity
JournalInternational Journal of Artificial Intelligence
Journal citation17 (1), pp. 34-56
ISSN0974-0635
Year2019
PublisherCentre for Environment & Socio-Economic Research Publications
Web address (URL)http://www.ceser.in/ceserp/index.php/ijai/article/view/5955
Publication dates
Published2019

Related outputs

A multi-Objective Optimisation Metaheuristic Hybrid technique for Forecasting the Electricity Consumption of the UAE: A Grey Wolf Approach
Andreas Karathanasopoulos, Chia Chun Lo, Sovan Mitra, Mohamed Osman, Hans-Jörg von Mettenheim and Slim Skander 2024. A multi-Objective Optimisation Metaheuristic Hybrid technique for Forecasting the Electricity Consumption of the UAE: A Grey Wolf Approach. Journal of Forecasting. Advanced online publication. https://doi.org/10.1002/for.3187

Catastrophe Bond Pricing In The Primary Market: The Issuer Effect And Pricing Factors
Chatoro, M, Mitra, S., Pantelous, A.A. and Shao, J. 2023. Catastrophe Bond Pricing In The Primary Market: The Issuer Effect And Pricing Factors. International Review of Financial Analysis. 85 102431. https://doi.org/10.1016/j.irfa.2022.102431

A Real Options Approach To Measuring Freedom In Sen’s Capabilities Approach
Mitra, S. 2022. A Real Options Approach To Measuring Freedom In Sen’s Capabilities Approach. International Journal of Sustainable Economy. 14 (1), pp. 98-110. https://doi.org/10.1504/IJSE.2022.119716

Optimal Feedback Control of Stock Prices Under Credit Risk Dynamics
Mitra, S., Jinghai Shao and Karathanasopoulos, Andreas 2022. Optimal Feedback Control of Stock Prices Under Credit Risk Dynamics. Annals of Operations Research. 313, pp. 1285-1318. https://doi.org/10.1007/s10479-021-04002-6

Keynesian Resurgence: Financial Stimulus And Contingent Claims Modelling
Clark, E., Mitra, S. and Jokung, O. 2020. Keynesian Resurgence: Financial Stimulus And Contingent Claims Modelling. International Journal of Mathematics in Operational Research. 17 (2), pp. 199-232. https://doi.org/10.1504/IJMOR.2020.109701

Downside risk measurement in regime switching stochastic volatility
Mitra, S. 2020. Downside risk measurement in regime switching stochastic volatility. Journal of Computational and Applied Mathematics. 378 112845. https://doi.org/10.1016/j.cam.2020.112845

Health Care Investment: The Case of Multiple Sources of Risk
Jokung, O. and Mitra, S. 2020. Health Care Investment: The Case of Multiple Sources of Risk. Asia-Pacific Financial Markets. 27, pp. 231-255. https://doi.org/10.1007/s10690-019-09291-3

An analysis of dollar cost averaging and market timing investment strategies
Lars Kirkby, J., Mitra, S. and Nguyen, D. 2020. An analysis of dollar cost averaging and market timing investment strategies. European Journal of Operational Research. 286 (3), pp. 1168-1186. https://doi.org/10.1016/j.ejor.2020.04.055

FinTech revolution: the impact of management information systems upon relative firm value and risk
Mitra, S. and Karathanasopoulos, A. 2020. FinTech revolution: the impact of management information systems upon relative firm value and risk. Journal of Banking and Financial Technology. 4, p. 175–187. https://doi.org/10.1007/s42786-020-00023-0

Ensemble Models in Forecasting Financial Markets
Karathanasopoulos, A., Mitra, S., Lo, C.C., Zaremba, A. and Osman, M. 2019. Ensemble Models in Forecasting Financial Markets. Journal of Computational Finance. 23 (3), pp. 101-119. https://doi.org/10.21314/JCF.2019.374

Risk lovers, mixed risk loving and the preference to combine good with good
Jokung, O. and Mitra, S. 2019. Risk lovers, mixed risk loving and the preference to combine good with good. International Journal of Management and Applied Science. 11 (4), pp. 295-313.

Post Global Financial Crisis Modelling: Credit Risk For Firms That Are Too Big To Fail
Clark, E., Mitra, S. and Jokung, O. 2019. Post Global Financial Crisis Modelling: Credit Risk For Firms That Are Too Big To Fail. International Journal of Financial Markets and Derivatives. 7 (1), pp. 15-39. https://doi.org/10.1504/IJFMD.2019.101235

Political Risk Modelling and Measurement From Stochastic Volatility Models
Mitra, S. 2019. Political Risk Modelling and Measurement From Stochastic Volatility Models. International Journal of Sustainable Economy. 11 (2), pp. 184-218. https://doi.org/10.1504/IJSE.2019.099064

Regression Based Scenario Generation: Applications For Performance Management
Mitra, S., Lim, S. and Karathanasopoulos, A. 2019. Regression Based Scenario Generation: Applications For Performance Management. Operations Research Perspectives. 6 100095. https://doi.org/10.1016/j.orp.2018.100095

Firm Value And The Impact of Operational Management
Mitra, S. and Karathanasopoulos, A. 2019. Firm Value And The Impact of Operational Management. Asia-Pacific Financial Markets. 26, pp. 61-85. https://doi.org/10.1007/s10690-018-9258-1

Stock-ADR Arbitrage: Microstructure Risk
Mitra, S. 2019. Stock-ADR Arbitrage: Microstructure Risk. Journal of International Financial Markets, Institutions and Money. 63 101132. https://doi.org/10.1016/j.intfin.2019.08.004

Efficient Option Risk Measurement With Reduced Model Risk
Mitra, S. 2017. Efficient Option Risk Measurement With Reduced Model Risk. Insurance: Mathematics and Economics. 72, pp. 163-174. https://doi.org/10.1016/j.insmatheco.2016.09.006

Stock Market Prediction Using Evolutionary Support Vector Machines: An Application To The ASE20 Index
Karathanasopoulos, A., Theofilatos, K.A., Sermpinis, D., Dunis, C., Mitra, S. and Stasinakis, C. 2016. Stock Market Prediction Using Evolutionary Support Vector Machines: An Application To The ASE20 Index. European Journal of Finance. 22 (12), pp. 1145-1163. https://doi.org/10.1080/1351847X.2015.1040167

Operational Risk: Emerging Markets, Sectors and Measurement
Mitra, S., Karathanasopoulos, A., Sermpinis, G., Dunis, C. and Hood, J. 2015. Operational Risk: Emerging Markets, Sectors and Measurement . European Journal of Operational Research. 241 (1), pp. 122-132. https://doi.org/10.1016/j.ejor.2014.08.021

Permalink - https://westminsterresearch.westminster.ac.uk/item/w3qwq/big-data-and-pac-learning-in-the-presence-of-noise-implications-for-financial-risk-management


Share this

Usage statistics

65 total views
0 total downloads
These values cover views and downloads from WestminsterResearch and are for the period from September 2nd 2018, when this repository was created.