Mean Reverting Asset Trading Project Presentation CSCI-5551 Grant Meyers.

Slides:



Advertisements
Similar presentations
Cash Flow Budgeting: Chap.13 §What is a cash flow budget used for? §What items are included in cash inflows and cash outflows? §What adjustments can be.
Advertisements

1 Chapter 15 Options Markets-The applications. 2 outline Features of options –Call vs., put, Long vs. short –In the money, out of the money and at the.
Risk and Return in Capital Markets
SUCCESSFUL COMBINATION INTERNET MARKETING BUSINESS FROM HOME.
THERE ARE NO WARRANTIES, EXPRESSED OR IMPLIED, AS TO ACCURACY, COMPLETENESS, OR RESULTS OBTAINED FROM ANY INFORMATION DISCUSSED DURING HAWKTRADE MEETINGS.
Options By: Kyle Lau, Matthew Cheung, and Fabian Kwan.
Quantitative Trading Strategy based on Time Series Technical Analysis Group Member: Zhao Xia Jun Lorraine Wang Lu Xiao Zhang Le Yu.
PHOENIX OPTION TRADING RULES. SUGGESTED TRADES  Suggested trades can come anytime our traders see an opportunity  Trades are ed as well as texted.
Stock Market. 14 year old investor What are Some of Your Favorite Companies?
Dr. Hassan Mounir El-SadyChapter 6 1 Black-Scholes Option Pricing Model (BSOPM)
Introduction to Stocks Basics of Investing I Spring 2014 Accounting 101` K. Robinson.
Lecture No.1 By M Fahad Siddiqi Lecture (Finance) IBMS.
The Disposition effect and Underreaction to news Abdullah Al-Ashi Jungha Woo Muna Albasman Talha Yasin 1.
OPTION PRICING OF CRUDE OIL: AN APPLICATION OF BLACK-SCHOLES MODEL Jamaladeen Abubakar Department of mathematics and statistics Hussaaini Adamu Federal.
Value at Risk: Market Risk Models Han Zhang Director, Head of Market Risk Analytics Corporate Market and Institutional Risk August 23, 2013 University.
Alternative Measures of Risk. The Optimal Risk Measure Desirable Properties for Risk Measure A risk measure maps the whole distribution of one dollar.
Chapter 13 Market-Making and Delta-Hedging.
Mathematical Finance Seminar. What is Mathematical Finance Other Terms Financial Engineering Quantitative Finance Computational Finance Mathematical Finance.
Initial Data Analysis Kunal Jain February 17, 2010 Economics 201FS.
10/7/ Financial Economics Chapter /7/ Financial Investment Economic investment Paying for new additions to the capital stock or new.
Chapter © 2010 South-Western, Cengage Learning Short Sell.
Unit 2: The Stock Market Lesson 1: What is a stock?
Stock Market Analysis and Personal Finance Mr. Bernstein Factors That Influence the Price of Stock pp September 2015.
THERE ARE NO WARRANTIES, EXPRESSED OR IMPLIED, AS TO ACCURACY, COMPLETENESS, OR RESULTS OBTAINED FROM ANY INFORMATION DISCUSSED DURING HAWKTRADE MEETINGS.
Online Financial Intermediation. Types of Intermediaries Brokers –Match buyers and sellers Retailers –Buy products from sellers and resell to buyers Transformers.
TRADING STRATEGIES FOR DEBT MARKET T Ramji
10-1 Decentralization: Responsibility Accounting, Performance Evaluation, and Transfer Pricing 10.
In Class – Week 2 Gains from Exchange Why do people willingly trade?
Additional Topics Additional items to address: Holding Period Return Short Selling with Margin Requirements.
Fang-Bo Yeh, Dept. of Mathematics, Tunghai Univ.2004.Jun.29 1 Financial Derivatives The Mathematics Fang-Bo Yeh Mathematics Department System and Control.
QUINN GAUMER ECE 259/CPS 221 Improving Performance Isolation on Chip Multiprocessors via on Operating System Scheduler.
Haksun Li
Stocks Branden Poe. The goals for this investment are to make money, Learn about the stock market, and learn more About the companies and their future.
Common Stock Valuation
© 2004 South-Western Publishing 1 Chapter 3 Basic Option Strategies: Covered Calls and Protective Puts.
Multiplication Facts Table of Contents 0’s 1’s 2’s 3’s 4’s 5’s 6’s 7’s 8’s 9’s 10’s.
Mean Reverting Asset Trading Research Topic Presentation CSCI-5551 Grant Meyers.
1 Dividend Policy - Basics by Binam Ghimire. Learning Objectives  Forms of Dividend  Dividend Payment Chronology  Factors affecting Dividend Payment.
Capital Asset Pricing Model (CAPM)
1 Ch.19 Divide and Conquer. 2 BIRD’S-EYE VIEW Divide and conquer algorithms Decompose a problem instance into several smaller independent instances May.
1 Strategies with Options Chapter Strategies with Options No slides Use of board.
How do Stock Markets Work?. Stocks involve more RISK than Bonds.
SS.8.FL.5.3Discuss that when people buy corporate stock, they are purchasing ownership shares in a business that if the nosiness is profitable, they will.
Matrix Factorization Reporter : Sun Yuanshuai
Using the TOS Analyze Tab to Make Better Trades
Jan 2016 Solar Lunar Data.
Risk and Return in Capital Markets
Team TLT Taehee Jung Lev Golod Temi N Lal
HW No. 3 Due in class W FEB p1 of 2

Mean Reverting Asset Trading
Cash Flow Budgeting: Chap.13
Mean Reverting Asset Trading
Mean Reverting Asset Trading
MONTH CYCLE BEGINS CYCLE ENDS DUE TO FINANCE JUL /2/2015

Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Prediction in Stock Trading
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Algorithms CSCI 235, Spring 2019 Lecture 8 Recurrences III
Investments: Analysis and Management Common Stock Valuation
Presentation transcript:

Mean Reverting Asset Trading Project Presentation CSCI-5551 Grant Meyers

Table of Contents 1. Review 2. Search Algorithm 3. Parallelization 4. Project Results

1. Review Mean Reverting Asset + Goal

Review – Mean Reverting Asset 

Example Mean Reverting Asset

Goal – Price Selection  We want to select 2 prices.  Price 1 is ‘buy’ price, this is an upper limit of when to start purchasing shares.  Price 2 is ‘sell’ price, this is a lower limit of when to start selling shares.

Goal – Price Selection  Better:

Goal – Optimal Price Selection  What are the best buy / sell prices for a given stock?  How do we find these prices?

Goal – Optimal Price Selection  What are the best buy / sell prices for a given stock?  Specific per stock.  How do we find these prices?  Algorithmic search on historic data

Table of Contents 1. Review 2. Search Algorithm 3. Parallelization 4. Project Results

2. Search Algorithm Recursive Refinement Search

Mathematical Model for Asset Price  A ‘Mean Reverting Asset’ is very similar to an Ito Process or Ornstein Uhlenbeck Process.  This similarity allows for a mathematical definition / prediction of what the stock price will do.  Search is based on historical data and recursively refined the more iterations the simulation is run.

Stochastic Differential Equation 

Stochastic Approximation 

Table of Contents 1. Review 2. Search Algorithm 3. Parallelization 4. Project Results

3. Parallelization Recursive Refinement Search

Equation Level Parallelism 

 Equations are ‘auto’ parallelized with Parallelize command.  Mathematica will split the expression parts into sub programs and distribute.

Question Level Parallelism  What is the best stock from a set of stocks S over time period P.  S = set of stock symbols, ie {“MSFT”, “AAPL”, “NFLX”, “CVX”, “AMZN”}  P = set of 2 dates, start and end, ie {“1 Jan 2015”, “13 Nov 2015”}  Allows for running all symbols independently of each other, then ‘combining’ results.  Done via ParallelSubmit on stock symbols.

Question Level Parallelism  What is the time period for stock S with in limited time period P.  S = stock symbol, ie {“MSFT”}  P = set of 2 dates, start search and end search, ie {“1 Jan 2015”, “13 Nov 2015”}  Allows for processing a single set of data, with multiple concurrent search threads.  ParallelSubmit with function to generate testing sets.

Table of Contents 1. Review 2. Search Algorithm 3. Parallelization 4. Project Results

Sample Results

Sample Results – Time Period  Best stock period for each: {“MSFT”, “AAPL”, “NFLX”, “CVX”, “AMZN”}  Time Period:Jul 2014 – Oct 2015 – Microsoft (MSFT)  Buy + Sell sets: 3 times of 233 shares.  Buy: $42.86Sell: $48.68Profit Per Share: $17.46 ($5.82)  2014 becomes 2015 – ~41% gain

Sample Results – Time Period 2  Best stock period for each: {“MSFT”, “AAPL”, “NFLX”, “CVX”, “AMZN”}  Time Period:Feb 2011 – Jul 2012 – Apple (AAPL)  Buy + Sell sets: 3 times of 132 shares.  Buy: $75.60Sell: $90.53 Profit Per Share: $44.79 ($14.93)  2011 becomes 2012 – ~60% gain

Sample Results – Time Period 3  Best stock period for each: {“MSFT”, “AAPL”, “NFLX”, “CVX”, “AMZN”}  Time Period:Sep 2013 – Jan 2015 – Netflix (NFLX)  Buy + Sell sets: 3 times of 33 shares.  Buy: $297.90Sell: $346.20Profit Per Share: $144.9 ($48.3)  2013 becomes 2015 – ~48% gain

Sample Results – Time Period 4  Best stock period for each: {“MSFT”, “AAPL”, “NFLX”, “CVX”, “AMZN”}  Time Period:Nov 2011 – Jul Chevron (CVX)  Buy + Sell sets: 5 times of 101 shares.  Buy: $98.72 Sell: $ Profit per Share: $47.9 ($9.58)  2011 becomes 2012 – 48% gain

Sample Results – Time Period 5  Best stock period for each: {“MSFT”, “AAPL”, “NFLX”, “CVX”, “AMZN”}  Time Period:Sep 2013 – Jan 2015 – Amazon (AMZN)  Buy + Sell sets: 3 times of 33 shares.  Buy: $297.90Sell: $346.20Profit Per Share: $144.9 ($48.3)  2013 becomes 2015 – ~48% gain

Sample Results – Best Stock in Period  Best stock of: {“MSFT”, “AAPL”, “NFLX”, “CVX”, “AMZN”}  Time Period:Nov 2010 – Nov 2015 – Apple (AAPL)  Buy + Sell sets: 3 times of 132 shares.  Buy: $75.60Sell: $90.53 Profit Per Share: $44.79 ($14.93)  2011 becomes 2012 – ~60% gain

Specific Questions to be Answered 1 Data Sample Related  Does the algorithm work when there is a macroscopic change in the overall market?  No. Some sort of capital preservation or opportunity cost maximum needs to be used.  Does changing the training & applying time windows affect the return? How much? Do longer windows fair better or shorter ones?  A) Yes. B) Depends. C) Inconclusive.  Are there any dependable seasonal fluctuations?  Inconclusive.  Does the asset ‘class’ affect the effectiveness of the algorithm?  Yes, most stocks are NOT mean reverting.

Specific Questions to be Answered 2 Performance Related  How fast can the Xeon server crunch the numbers?  How fast can the Hydra server crunch the numbers?  Is there a better way to format the data than the default JSON format?  Given the use of common mathematical operations, could they be switched out to a format that uses matrix multiplication?