The prediction parameters shares tab is used to specify the size of trades used when calculating prediction profits. The size of trades is important because it is the basis for profit and commission calculations during the training and backtesting. For the profit and commission statistics to be realistic, you should specify a trading size that is closest to your actual trading style.
The parameters on this tab may or may not be visible depending upon the currently selected Prediction Wizard Interface Options. Press the Options button to change the Prediction Wizard Interface Options. For more information see Prediction Wizard Interface Options.
- Specify the Size of trades used to determine prediction profit.
Buy a fixed number of shares ‘ Calculates profits using the specified number of shares
Buy a fixed dollar amount of shares ‘ Calculates profits using a varying number of shares based upon the specified dollar amount and the closing price when the entry signal occurs. Shares Traded = (Dollars Specified / Entry Price) rounded down to the nearest whole number of shares.
Buy as many shares as possible with current account balance ‘ Calculates profits using a varying number of shares based upon the current account balance and the closing price when the entry signal occurs. The current account balance is increased/decreased by the realized profit/loss of each trade. Shares Traded = (Current Account Balance / Entry Price) rounded down to the nearest whole number of shares.
Buy shares in round lot of ‘ Rounds down the number of shares traded to a multiple of the specified number of shares. As an example, if the round lot shares is set to 100 and the number of shares to be traded is 299, then the actual number of shares traded will be 200.
When you are satisfied with the prediction parameters to be used when training and optimizing press the OK button to return to the Prediction Wizard.
Topics of Interest:
What are Neural Networks?
Neural Network – Network Criteria Discussion (General)
Neural Network – Network Criteria Discussion (Objective)
Neural Network – Network Criteria Discussion (Advanced)
Troubleshooting Your Model – What to Do if You Feel You Haven’t Been Successful