Capitalico / Chart Pattern Matching in Financial Trading Using RNN

8,684 views

Published on

Capitalico is a web/mobile platform that utilizes deep learning to help financial traders build automated trading system by understanding their trading charts. In this talk I show many of the techniques we developed to achieve the best performance and accuracy in deep learning for sequence pattern matching.

Published in: Software
0 Comments
4 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
8,684
On SlideShare
0
From Embeds
0
Number of Embeds
6,789
Actions
Shares
0
Downloads
77
Comments
0
Likes
4
Embeds 0
No embeds

No notes for slide

Capitalico / Chart Pattern Matching in Financial Trading Using RNN

  1. 1. 1 Make you trade ideas into AI. Start free. On mobile. Hitoshi Harada CTO hitoshi@alpacadb.com http://alpaca.ai Chart Pattern Matching in Financial Trading Using RNN http://www.capitalico.com
  2. 2. Entry Point What Technical Traders Are Looking For 2
  3. 3. Diversity Of The Pattern - All Downtrend 3
  4. 4. • Fuzzy Pattern Recognition for everyone • Generalization (no hand crafted features) • Multiple time series (OHLC price + indicators) • Time scale, value scale, distortion James N.K. Liu *, Raymond W.M. Kwong : Automatic extraction and identification of chart patterns towards financial forecast, 2006 Problem And Needs - Fuzzy Pattern Recognition Zhe Zhang, Jian Jiang, Xiaoyan Liu, Ricky Lau, Huaiqing Wang, Rui Zhang: A Real Time Hybrid Pattern Matching Scheme for Stock Time Series, 2010 4
  5. 5. How To Solve The Problem? 5 SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS, Hinton, et al. 2013 Capitalico “ah” “p” “down trend”
  6. 6. Interactive Training Data Collection & Training 6
  7. 7. • Train by what you see & judge • No programming nor conditional setting, but purely from charts like traders do
 • Multi-dimensional input • Not only the single time- series data of price movement but also various indicators altogether Our Approach - Fuzzy Pattern Recognition without Programming 7
  8. 8. • Network • Input: • N-dim Fully Connected Layer • LSTM Layer x 2 or 4 ( x250 units ) • Fully Connected Layer ( x250 units ) • Dropout • Sigmoid • Output: • 1-dim confidence level
 • Training • Align with fixed number of candles • Mean squared error for loss • AdaDelta for optimizer • BPTT through aligned length • Data • 1k+ samples collected by experts • about hundred instances for each strategy Input LSTM LSTM Fully Connected Output Fully Connected Time Experiments Deep Learning Based Approach 8 Sigmoid Input LSTM LSTM Fully Connected Output Fully Connected Sigmoid Input LSTM LSTM Fully Connected Output Fully Connected Sigmoid
  9. 9. x-axis: time (1.0=entry point) blue: training data / orange: testing data Experiments Fitting Reasonably y-axis:confidence 9
  10. 10. Experiments Framework 10
  11. 11. Dropout • Dropout vs # of training samples • Bigger Mini-Batches by looping samples • Made it Adaptive depending on importance 11 dropout enabled (x: iteration count, y: loss) dropout w/ bigger mini-batches (x: iteration count, y: loss)
  12. 12. Forget Gate Bias (Learning To Forget: Continual Prediction With Lstm, Felix Et Al.) 12
  13. 13. Trial And Error To Speed Up Training 13 • Dynamic Dropout • Dynamic Batchsize • Multi-GPU Training • Other Frameworks like Keras • GRU • IRNN • Lot more…
  14. 14. 14 • Previous studies have limitations to difficulty of feature crafting. • LSTM based deep neural network fits well with individual patterns. • LSTM-variant doesn’t make much difference, but forget-gate bias, normalization, preprocessing, and modeling etc. matter • Build better base model by pre-training • Reinforcement Learning using profit and risk preference • Visualize and rationalize LSTM decision making • Generative Model Conclusion & Future Work 14
  15. 15. QUESTIONS AND ANSWERS http://alpaca.ai / info@alpacadb.com http://www.capitalico.com Make you trade ideas into AI. Start free. On mobile.
  16. 16. • Ken-ichi Kainijo and Tetsuji Tanigawa:
 Stock Price Pattern Recognition - A Recurrent Neural Network Approach -, 1990 • S Hochreiter, J Schmidhuber:
 Long short-term memory, 1997 • FA Gers, J Schmidhuber, F Cummins:
 Learning to forget: Continual prediction with LSTM, 2000 • James N.K. Liu *, Raymond W.M. Kwong:
 Automatic extraction and identification of chart patterns towards financial forecast, 2006 • X Guo, X Liang, X Li:
 A stock pattern recognition algorithm based on neural networks, 2007 • Z Zhang, J Jiang, X Liu, R Lau, H Wang:
 A real time hybrid pattern matching scheme for stock time series, 2010 • A Graves, A Mohamed, G Hinton:
 Speech recognition with deep recurrent neural networks, 2013 • A Graves, N Jaitly:
 A Mohamed, Hybrid speech recognition with deep bidirectional LSTM, 2013 • Tara N. Sainath, Oriol Vinyals, Andrew Senior, Has¸im Sak:
 CONVOLUTIONAL, LONG SHORT-TERM MEMORY, FULLY CONNECTED DEEP NEURAL NETWORKS References 16
  17. 17. Need For Gpu And Distributed Computation 17 • Model Training • Takes around 10 minutes on a single GPU core • Requires 2GB of GPU RAM • Backtesting • Calculate various metrics over the historical data • Livetesting • Thousands of models need to monitor live candles and update the state of LSTM
  18. 18. Need For Distributed Computation 18 DB Postgresql Redis etcd Load Balancer WEB Flask tesla k80 WORKER Live Market Watch Market Data Historical Real time Queue Celery Trading Algos = ~10MB x1-10K

×