Presentation is loading. Please wait.

Presentation is loading. Please wait.

Machine Learning in Stock Price Trend Forecasting BY PRADEEP KUMAR REDDY MUSKU.

Similar presentations


Presentation on theme: "Machine Learning in Stock Price Trend Forecasting BY PRADEEP KUMAR REDDY MUSKU."— Presentation transcript:

1 Machine Learning in Stock Price Trend Forecasting BY PRADEEP KUMAR REDDY MUSKU

2 Stock prices are dynamic and depends on known and unknown factors Stock prices are dynamic and depends on known and unknown factors Stock Prediction Methodologies Stock Prediction Methodologies Fundamental Fundamental Technical Technical Efficient Market Hypothesis(EMH) Efficient Market Hypothesis(EMH) Strong Strong Semi Strong Semi Strong Weak Weak

3 Implementation Data Collection Data Collection Model Selection Model Selection Next-Day model Next-Day model Long-Term model Long-Term model Feature Selection Feature Selection

4 Data Collection Training data is collected from Bloomberg database Training data is collected from Bloomberg database 3M stock was picked and it contains 1471 data points (1/9/2008 to 11/8/2013) 3M stock was picked and it contains 1471 data points (1/9/2008 to 11/8/2013) There are 16 features that can be used for this learning theory. Some of them are There are 16 features that can be used for this learning theory. Some of them are PE ratio PE ratio 50-day moving average 50-day moving average Current Enterprise value Current Enterprise value

5 Model Selection Learning Theories used: Learning Theories used: Logistic Regression Logistic Regression Gaussian Discriminant analysis Gaussian Discriminant analysis Quadratic Discriminant analysis Quadratic Discriminant analysis Support Vector Machine(SVM) Support Vector Machine(SVM)

6 Accuracy = The number of days that the model correctly classified the testing data total no of training days Accuracy = The number of days that the model correctly classified the testing data total no of training days Next – Day Model Next – Day Model ModelLogistic Regression GDAQDASVM Accuracy44.5%46.4%58.2%55.2%

7 Long – Term Model Long – Term Model Predicting a stock sign of difference between tomorrow’s stock price and that of certain days ego Predicting a stock sign of difference between tomorrow’s stock price and that of certain days ego

8 Feature Selection

9 Trading Strategy Used 990 of the 1470 data points to fit the model. Used 990 of the 1470 data points to fit the model. Made the investment decision based on the model. Made the investment decision based on the model.

10 Comparison This model has outrun the performance of the stock, with an annualized return of 19.3% vs 12.5% This model has outrun the performance of the stock, with an annualized return of 19.3% vs 12.5%


Download ppt "Machine Learning in Stock Price Trend Forecasting BY PRADEEP KUMAR REDDY MUSKU."

Similar presentations


Ads by Google