CS297 Proposal
Algorithmic Trading
Sonal Kabra (sonal.kabra@sjsu.edu)
Advisor: Dr. Chris Pollett
Description:
Algorithmic trading is the process of using a computer program to follow a defined set of instructions for placing a trades at speeds, complexity, or frequency beyond what a human trader can do. Algorithmic trading can be based on timing, price, quantity or any mathematical model. For this project I will use St Louis Fed for economic indicators and Qandl stock data sets. I will build multi-layer neural networks to predict buy, sell or hold classification for a single or a portfolio of stocks for time scales of one day, one month, and one year. I will also work on neural networks to try to improve the estimates of stocks or economic volatility measures.
Schedule:
Week 1:
Sep 7 - Sep 13 | Talk about the project in detail with the advisor. Prepare and deliver CS 297 Proposal. |
Week 2:
Sep 14 - Sep 20 | Presentation on Algorithmic trading and techniques |
Week 3:
Sep 21 - Sep 27 | Understand and manipulate previous years stock data set in python |
Week 4:
Sep 28 - Oct 4 | Deliverable 1:Measure volatility of stock by inputing stock ticker in program |
Week 5:
Oct 5 - Oct 11 | Understanding and implementing Neural Net with respect to algorithmic trading |
Week 6:
Oct 12 - Oct 18 | Deliverable 2:Implement the simple neural net for estimating starting month of give dataset |
Week 7:
Oct 19 - Oct 25 | Understanding and building deep learning algorithms using python library |
Week 8:
Oct 26 - Nov 1 | Understand the K- nearest neighbor and Decision tree algorithm for stock prediction |
Week 9:
Nov 2 - Nov 8 | Deliverable 3:Implement the K- nearest neighbor and Decision tree algorithm for stock prediction |
Week 10:
Nov 9 - Nov 15 | Build program to work with portfolio of stock |
Week 11:
Nov 16 - Nov 22 | Continue work from week 11 |
Week 12:
Nov 23 - Nov 29 | Deliverable 4:Implement program to work with the portfolio of stock |
Week 13:
Nov 30 - Dec 6 | Start compiling CS 297 Report |
Week 14:
Dec 7 - Dec 13 | Deliverable 5:CS297 Report |
Deliverables:
The full project will be done when CS298 is completed. The following will
be done by the end of CS297:
1. Measure volatility of stock by inputing stock ticker
2. Implement the simple neural net for estimating starting month of give dataset
3. Implement the K- nearest neighbor and Decision tree algorithm for stock prediction
4. Get the previous program to work with the portfolio of stock
5. CS297 Report
References:
[2015] Basics of Algorithmic Trading: Concepts and Examples. Shobhit Seth. Investopedia. 2015.
[2013] ALGORITHMIC TRADING USING MACHINE LEARNING TECH-NIQUES: FINAL REPORT. Shao, Chenxu, and Zheming Zheng. Learning 5. 2013.
|