Stock Price Prediction Using Reinforcement Learning

Slides:



Advertisements
Similar presentations
Neural Networks in Financial Analysis
Advertisements

Stock Price Prediction Based on Social Network A survey Presented by: CHEN En.
Learning to Trade via Direct Reinforcement
Reinforcement learning
Reinforcement Learning (II.) Exercise Solutions Ata Kaban School of Computer Science University of Birmingham 2003.
TEMPORAL DIFFERENCE LEARNING Mark Romero – 11/03/2011.
1 Temporal-Difference Learning Week #6. 2 Introduction Temporal-Difference (TD) Learning –a combination of DP and MC methods updates estimates based on.
A Generalized Model for Financial Time Series Representation and Prediction Author: Depei Bao Presenter: Liao Shu Acknowledgement: Some figures in this.
Brian Merrick CS498 Seminar.  Introduction to Neural Networks  Types of Neural Networks  Neural Networks with Pattern Recognition  Applications.
Università di Milano-Bicocca Laurea Magistrale in Informatica Corso di APPRENDIMENTO E APPROSSIMAZIONE Lezione 6 - Reinforcement Learning Prof. Giancarlo.
Chapter 8: Generalization and Function Approximation pLook at how experience with a limited part of the state set be used to produce good behavior over.
Reinforcement Learning
Slide 1 EE3J2 Data Mining EE3J2 Data Mining Lecture 15: Introduction to Artificial Neural Networks Martin Russell.
Reinforcement Learning
Reinforcement Learning Mitchell, Ch. 13 (see also Barto & Sutton book on-line)
1 Hybrid Agent-Based Modeling: Architectures,Analyses and Applications (Stage One) Li, Hailin.
Mr. Perminous KAHOME, University of Nairobi, Nairobi, Kenya. Dr. Elisha T.O. OPIYO, SCI, University of Nairobi, Nairobi, Kenya. Prof. William OKELLO-ODONGO,
Chapter Ten The Efficient Market Hypothesis Copyright © 2004 Pearson Education Canada Inc. Slide 10–3 Computing the Price of Common Stock Basic Principle.
1 Quality of Experience Control Strategies for Scalable Video Processing Wim Verhaegh, Clemens Wüst, Reinder J. Bril, Christian Hentschel, Liesbeth Steffens.
Making Decisions CSE 592 Winter 2003 Henry Kautz.
Preliminary Analysis of the SEE Future Infrastructure Development Plan and REM Benefits.
NEURAL NETWORKS FOR TECHNICAL ANALYSIS: A STUDY ON KLCI 授課教師:楊婉秀 報告人:李宗霖.
Discounted Cash Flow (DCF) Analysis Tutorial This presentation is to be used ONLY as a template for DCF Analysis presentations. In no way should it reflect.
The Security Market Line (SML) aka The Capital Asset Pricing Model (CAPM) The Capital Asset Price Model is E(R A ) = R f + [E(R M ) - R f ] x A Expected.
© 2008 Pearson Education Canada7.1 Chapter 7 The Stock Market, the Theory of Rational Expectations, and the Efficient Markets Hypothesis.
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
Exponential Moving Average Q- Learning Algorithm By Mostafa D. Awheda Howard M. Schwartz Presented at the 2013 IEEE Symposium Series on Computational Intelligence.
Temporal Difference Learning By John Lenz. Reinforcement Learning Agent interacting with environment Agent receives reward signal based on previous action.
Data Mining Techniques in Stock Market Prediction
Dr. Tucker Balch Associate Professor School of Interactive Computing Computational Investing, Part I 041: Company Value Find out how modern electronic.
Chapter 27 Theory of Rational Expectations and Efficient Capital Markets.
Learning Theory Reza Shadmehr & Jörn Diedrichsen Reinforcement Learning 2: Temporal difference learning.
Dr. Tucker Balch Associate Professor School of Interactive Computing CS 7646: Machine Learning for Trading Company Value Find out how modern electronic.
A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting Huang, C. L. & Tsai, C. Y. Expert Systems with Applications 2008.
Fuzzy Reinforcement Learning Agents By Ritesh Kanetkar Systems and Industrial Engineering Lab Presentation May 23, 2003.
Tanja Magoč, François Modave, Xiaojing Wang, and Martine Ceberio Computer Science Department The University of Texas at El Paso.
CHECKERS: TD(Λ) LEARNING APPLIED FOR DETERMINISTIC GAME Presented By: Presented To: Amna Khan Mis Saleha Raza.
Dr. Tucker Balch Associate Professor School of Interactive Computing Computational Investing, Part I 193: Information and Technical Analysis: Some Example.
Non-Bayes classifiers. Linear discriminants, neural networks.
Capital Asset Pricing and Arbitrage Pricing Theory
Neural Networks Chapter 7
CUHK Learning-Based Power Management for Multi-Core Processors YE Rong Nov 15, 2011.
Reinforcement Learning with Laser Cats! Marshall Wang Maria Jahja DTR Group Meeting October 5, 2015.
Soft Computing methods for High frequency tradin.
7-1 (1) Computing the Price of Common Stock Basic Principle of Finance Value of Investment = Present Value of Future Cash Flows One-Period Valuation Model.
Financial Data mining and Tools CSCI 4333 Presentation Group 6 Date10th November 2003.
Reinforcement Learning for Mapping Instructions to Actions S.R.K. Branavan, Harr Chen, Luke S. Zettlemoyer, Regina Barzilay Computer Science and Artificial.
Data Mining: Neural Network Applications by Louise Francis CAS Convention, Nov 13, 2001 Francis Analytics and Actuarial Data Mining, Inc.
Deep Learning and Deep Reinforcement Learning. Topics 1.Deep learning with convolutional neural networks 2.Learning to play Atari video games with Deep.
A Method to Approximate the Bayesian Posterior Distribution in Singular Learning Machines Kenji Nagata, Sumio Watanabe Tokyo Institute of Technology.
Prepared by Fayes Salma.  Introduction: Financial Tasks  Data Mining process  Methods in Financial Data mining o Neural Network o Decision Tree  Trading.
An Automated Trading System using Recurrent Reinforcement Learning
Investment Management
Lecture Presentation Software to accompany Investment Analysis and Portfolio Management Eighth Edition by Frank K. Reilly & Keith C. Brown Chapter 12.
Online Multiscale Dynamic Topic Models
Adversarial Learning for Neural Dialogue Generation
A Crash Course in Reinforcement Learning
Chapter 6: Temporal Difference Learning
Chapter 5: Monte Carlo Methods
Review Fundamental analysis is about determining the value of an asset. The value of an asset is a function of its future dividends or cash flows. Dividends,
Topic #4 Financial Instruments in the Market: II Stocks
Reinforcement Learning
Chapter 6: Temporal Difference Learning
Time Series Forecasting Accelerator
Forecasting - Introduction
Reinforcement Learning (2)
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 7
Reinforcement Learning (2)
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 7
Presentation transcript:

Stock Price Prediction Using Reinforcement Learning 이 재 원

Introduction Analytical methods Technical analysis Fundmental analysis EMH (efficient market hypothesis) Traditional time series forecasting Chaos theory Computer techniques Neural network Fuzzy logic / Expert system

Adopt reinforcement learning “Economic history is a never-ending series of episodes based on falsehoods and lies, not truths. It represents the path to big money. The object is to recognize the trend whose premise is false, ride that trend, and step off before it is discredited.” - George Soros – The proposed method Adopt reinforcement learning Suitable for representing delayed rewards as well as immediate rewards

Reinforcement Learning Agent-environment interaction Agent Action at State st Reward rt rt+1 Environment st+1

 evaluation V improvement Value function Generalized policy iteration VV  greedy(V )  V

TD Algorithms Learn from raw experience without a model Bootstrap update in part on an existing estimate suitable for continuous tasks TD(0) the simplest TD algorithm

Stock Price Changes in TD View State vector Raw daily data (open price, close price, ...) Technical indicators Disparities Moving averages Stochastic oscillator etc.

Reward Relative rate of change in close price The values of states can be calculated from the rewards using discounting factor  (0 <  < 1)

e.g., The value of stock A at time step 0 is greater than that of stock B

Function Approximation by Neural Network Parameter vector Vector of connection weights of the net Gradient descent

Experimental result  

Future works Predictability Rule-based approach/other learning models Policy optimization optimal profit ratio optimal stop loss(risk management) optimal holding period Asset allocation Other investment opportunities Foreign exchange Futures/options