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

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

Post on 03-Jan-2016

213 views

Category:

Documents

0 download

Embed Size (px)

TRANSCRIPT

<p>Machine Learning in Stock Price Trend ForecastingByPradeep Kumar Reddy MuskuStock prices are dynamic and depends on known and unknown factorsStock Prediction MethodologiesFundamentalTechnicalEfficient Market Hypothesis(EMH)StrongSemi StrongWeak2ImplementationData CollectionModel SelectionNext-Day modelLong-Term modelFeature SelectionData CollectionTraining data is collected from Bloomberg database3M 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 arePE ratio50-day moving averageCurrent Enterprise valueModel SelectionLearning Theories used:Logistic RegressionGaussian Discriminant analysisQuadratic Discriminant analysisSupport Vector Machine(SVM)Accuracy = The number of days that the model correctly classified the testing data total no of training days</p> <p>Next Day ModelModelLogistic RegressionGDAQDASVMAccuracy44.5%46.4%58.2%55.2%Long Term Model Predicting a stock sign of difference between tomorrows stock price and that of certain days ego</p> <p>Feature SelectionTrading StrategyUsed 990 of the 1470 data points to fit the model.Made the investment decision based on the model.</p> <p>ComparisonThis model has outrun the performance of the stock, with an annualized return of 19.3% vs 12.5%</p>