Predictive Learning of Factor Based Strategies using Deep Neural Networks for Investment and Risk Management
- 1. Predictive Learning of Factor Based Strategies using Deep Neural Networks for Investment and Risk Management Yigal Jhirad March 27, 2018 NVIDIA GTC 2018: Deep Learning & AI Conference Silicon Valley
- 2. GTC 2018: Table of Contents I. Deep Learning in Finance — Forecasting Factor Regimes — Machine Learning Landscape — Deep Learning + Neural Networks — Neural Networks – ANN, RNN, LSTM — Optimization II. Parallel Implementation III. Summary IV. Author Biographies DISCLAIMER: This presentation is for information purposes only. The presenter accepts no liability for the content of this presentation, or for the consequences of any actions taken on the basis of the information provided. Although the information in this presentation is considered to be accurate, this is not a representation that it is complete or should be relied upon as a sole resource, as the information contained herein is subject to change. 2
- 3. 3 GTC 2018: Deep Learning Investment & Risk Management — Forecast Market Returns, Volatility Regimes, Factor Trends, Liquidity, Economic Cycles — Big Data including Time Series Data, Interday, and Intraday — Neural Networks: Black Box/Pattern Recognition — Complement existing quantitative and qualitative signals Challenges include state dependency and stochastic nature of markets — Time series — Overfitting/Underfitting — Stochastic Nature of Data 3
- 4. GTC 2018: Factor Analysis Factor Analysis — Identify factors that are driving the market and predict relative factor performance — Establish a portfolio of sectors or stocks that benefits from factor performance — Align risk management with forecasts of volatility Identifying and Assessing factors driving performance — Look at factors such as Value vs. Growth, Large Cap vs. Small Cap, Volatility Period:12/2016-12/2017 4
- 5. Artificial Intelligence Data: Structured/Unstructured Asset Prices, Volatility Fundamentals ( P/E,PCE, Debt to Equity) Macro (GDP Growth, Interest Rates, Oil prices) Technical(Momentum) News Events Machine Learning Unsupervised Learning Cluster Analysis Principal Components Expectation Maximization Supervised Learning (Linear/Nonlinear) Deep Learning Neural Networks Support Vector Machines Classification & Regression Trees K-Nearest Neighbors Regression Reinforcement Learning Deep Learning Q-Learning Trial & Error 5
- 6. Inputs: Fundamental/Macro/Technical Price/Earnings Momentum/RSI Realized & Implied Volatility Value vs Growth GDP Growth/Interest Rates Dollar Strength Credit Spreads Feature(Factor)Identification & Regularization Forecast: Market Returns Risk/Volatility Liquidity ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂𝑥2 𝑥1 𝑥3 𝑥4 𝑥5 Supervised Learning: Neural Networks 6
- 7. Supervised Learning: Neural Networks Forecast: Market Returns Risk/Volatility Liquidity ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂𝑥2 𝑥1 𝑥3 𝑥4 𝑥5 Forecast: Market Returns Risk/Volatility Liquidity ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂ ∑|∂𝑥2 𝑥1 𝑥3 𝑥4 𝑥5 Simple Feed-Forward Neural Network Recurrent Neural Network 7
- 8. Neural Network Work Flow Input Data: Prices, Fundamentals, Macro, Technical Structured/Unstructured Data Pre-Processing Normalization & Determine Model Parameters Forecast Outcome Training/Validation/Test Feedforward/Back Propagation/Genetic Algorithm 8
- 9. Next Hidden Layer/Output 𝒘 𝒇 𝒘 𝒐𝒘 𝒇𝒊 𝒘𝒊 𝒉 𝒕 𝐗 𝒊 𝒄 𝒕 𝒉 𝒕−𝟏 𝒉 𝒕Forget Gate Input Gate Output Gate 𝒉 𝒕 𝒄 𝒕−𝟏 Long Term Memory Short Term Memory NextTimePeriodt+1 PreviousTimePeriodt-1 Time + GTC 2018: LSTM ○ ○ ○ ({h1,…,hm}(t-1)), ({xi,…, xn}(t)) {c1,…,cm}(t-1) f1,…,fm i1,…,im g1,…,gm o1,…,om ({x1,…, xn}(t)) {h1,…,hm}(t-1) Economic GDP Interest Rates Currency Style/Factor Momentum Value/Growth Volatility Fundamental P/E Debt/Equity Yield X∈ℝfactors×timeperiods Inputs/Factors t t+1t-1 9
- 10. GTC 2018: Predicting Volatility Regimes with LSTM 10
- 11. 11 GTC 2018: Neural Networks Neural Networks — Feed-Forward vs. Recurrent Neural Networks — LSTM captures the temporal nature of financial data — Complement existing quantitative and qualitative signals Advantages — Captures non-linearity that are prevalent in financial data — Time Sequencing, Pattern Recognition — Modularity — Parallel Processing Considerations — Black Box — Overfitting/Underfitting — Optimization/Local Minima 11
- 12. GTC 2018: Genetic Algorithms • Gradient Descent may not be efficient • Local Minimums pose a challenge • Genetic Algorithms complement traditional optimization techniques • Apply the computational power within CUDA to create a more robust evolutionary algorithm to drive multi-layer Neural Networks Local Maximum Local Minimum Local Maximum 12
- 13. Summary Utilize an LSTM Neural Network to identify market regimes Propose an Augmented LSTM Process that can help drive deep learning by identifying appropriate factors across market regimes — Enhance construction by utilizing Optimization with Constraints function instead of penalty function — Utilize Genetic algorithms CUDA leverages GPU Hardware providing computational power to drive optimization algorithms and Deep Learning Application in Investment and Risk Management 13
- 14. 14 Author Biographies Yigal D. Jhirad, Senior Vice President, is Director of Quantitative and Derivatives Strategies and a Portfolio Manager for Cohen & Steers’ options and real assets strategies. Mr. Jhirad heads the firm’s Investment Risk Committee. He has 30 years of experience. Prior to joining the firm in 2007, Mr. Jhirad was an executive director in the institutional equities division of Morgan Stanley, where he headed the company’s portfolio and derivatives strategies effort. He was responsible for developing, implementing and marketing quantitative and derivatives products to a broad array of institutional clients, including hedge funds, active and passive funds, pension funds and endowments. Mr. Jhirad holds a BS from the Wharton School. He is a Financial Risk Manager (FRM), as Certified by the Global Association of Risk Professionals.