the data the best. In model-based strategy building, we start with a model of a market inefficiency, construct a mathematical representation(eg price, returns) and test its validity in the long term. We can use these three indicators, to build our model, and then use an appropriate ML algorithm to predict future values. This way the test data stays untainted and we dont use any information from test data to improve our model. So sit back and enjoy the part two of Machine Learning and Its Application in Forex Markets. DataFrame(index dex, columns ) basis_X'mom3' difference(data'basis 4) basis_X'mom5' difference(data'basis 6) basis_X'mom10' difference(data'basis 11) basis_X'rsi15' rsi(data'basis 15) basis_X'rsi10' rsi(data'basis 10) basis_X'emabasis3' ewm(data'basis 3) basis_X'emabasis5' ewm(data'basis 5) basis_X'emabasis7' ewm(data'basis 7) basis_X'emabasis10' ewm(data'basis 10) basis_X'basis' data'basis' basis_X'vwapbasis' basis_X'swidth' data'stockTopAskPrice' - data'stockTopBidPrice' basis_X'fwidth' data'futureTopAskPrice' - data'futureTopBidPrice' basis_X'btopask' data'stockTopAskPrice'.
On the other hand, we first look for price patterns and attempt to fit an algorithm to it in data mining approach. Recently I have followed an online course on machine learning to understand the current hype better. Lets try normalization to conform them to same scale and also enforce some stationarity. You can follow along the steps in this model using this IPython notebook. Are you predicting, price at a future time, future Return/Pnl, Buy/Sell Signal, Optimizing Portfolio Allocation, try Efficient Execution etc? For example what might seem like an upward trending pattern explained well by a linear regression may turn out to be a small part of a larger random walk! This may be a cause of errors in your model; hence normalization is tricky and you have to figure what actually improves performance of your model(if at all). Long rule (PriceSAR) -0.0150 (Price SAR) -0.0050 macd -0.0005. It however doesnt take into account fees/transaction costs/available trading volumes/stops etc. Framing rules for a forex strategy using SVM.
If you find yourself needing a large number of complex features to explain your data, you are likely over fitting Divide your available data into training and test data and always validate performance on Real Out of Sample data before using your model to trade. The SVM algorithm seems to be doing a good job here. DO NOT go back and re-optimize your model, this will lead to over fitting!