Addaptron Software released a new Stock Market Forecast Tools SMFT-2. It is an integrated advanced system that is the next generation improved software based on older SMFT-1 version and a few recent development projects.
Most prediction modules provided with back-test calculation to estimate the accuracy of forecast within the recent performance periods. Additionally, the back-testing computations play an important role if more than one method is used. It allows estimating a weight of each method in a composed result; the weights that are proportional to the ability of the methods to predict the price.
SMFT-2 currently includes five major modules:
- TA Predictor – prediction for day or week period based on technical analysis, pattern recognition and Neural Networks (generates composite result). Back-analysis models optimization and batch calculation for comparative analysis included.
- Waves – Elliott Wave model: back-test optimization, up to 10 waves forecast.
- Cycles – prediction based on cycle analysis.
- Week day – search for maximum performance using price behavior depending on week day. It allows discovering the best entry/exit days of week; batch calculation included.
- Month day – search for maximum performance using price behavior depending on month day. It allows discovering the best entry/exit days of month; batch calculation included.
The implemented methods are statistically proven and widely used. All modules share the same EOD (end-of-day) input data. The software is provided with a free Downloader that allows downloading EOD historical quotes files from the Internet for free. A fully-functional software SMFT-2 during initial 30-day period is free. The software and associated documentation are delivered via download links over the Internet. For technical requirements, installation instruction, and download link, visit SMFT-2 download page.
Any prediction can fail but if it is combined with well-tested buy-sell rules, the result is much better. Addaptron Software provides predictions of major ETFs prices (Open, High, Low, Close) for the next day. This article describes one of the simplest algorithms to use one-day candle prediction data. The algorithm consists of four simple rules:
- Place Buy Limit order with predicted Low price before the stock market is opened.
- As soon as the Buy Limit order is completed, place Sell Limit order with predicted High price.
- Cancel the order if it is not completed during the first half of the stock market day.
- If the stock market is about to close but the order is not completed, cancel the Sell Limit order and place Sell Market order.
The following charts and tables demonstrate one of the practical examples of described above approach (symbol BOIL).
Predicted and actual prices chart (dark green and red filled candles – predicted, light green and red line candles – actual):
Predicted and actual prices table:
Intraday performance chart (actual prices) for the same period:
The result of using the described algorithm:
The example is based on the following assumptions: 300 shares are used for trading, transaction fee is $10 so that 2 transactions (buy and sell) within day cost $20. Another example (symbol SSO) can be find here
Addaptron Software is pleased to announce the release of updated 2012.06.01 version of Trading Decision Support System TraDeSS-1. Now Simulation module allows optimizing algorithms and their parameters, as well as, performing comparative analysis for many symbols. At the end of batch mode simulation, it prints a summarized list of best buy-sell algorithms and parameters configuration for each symbol. The list is sorted from best to worst performers.
Now Relative Performance Forecast module allows printing output results in HTML-format that include additional information about prediction. It shows the forecast generated by each selected method, as well as, the weights of forecasts that were assigned in a composite forecast. If more than two methods are used, table includes RMSD (it is normalized root-mean-square deviation that is to estimate the degree of forecasts concurrence; the less amount means better consensus among different methods).
The new version is able to read input historical prices files of three different formats. The software recognizes these formats automatically. To enable reading any other format files, users should send the request.
The two charts below show a possible behavior of S&P-500 index for the next week, May 16-20, 2011. The first chart is neural network forecast, the second one is pattern similarity forecast. Both methods predict a slight uptrend.
The chart shows S&P-500 index forecast for the period starting from February 14, 2011. The calculation has been performed using Stock Market Predictor SMAP-3 (cycles analysis). The prediction is a possible downtrend starting from February 16-17 and then reversal to uptrend at the beginning of March.
The chart shows S&P-500 index possible behavior for February 7 – 11, 2011. The forecast is a fluctuation with a small downtrend. The prediction has been calculated using the pattern recognition feature of Investment Analyzer InvAn-4.
The charts show S&P-500 index possible behavior for January 31 – February 4, 2011. The forecast is a fluctuation with an eventual uptrend. The graphs have been calculated using Neural Network Stock Trend Predictor NNSTP-2 (upper chart) and pattern similarity forecast by Investment Analyzer InvAn-4 (below).
The chart shows S&P-500 index forecast for the period from January 24 to January 28, 2011. The possible ^GSPC behavior is a fluctuation with a slight uptrend. The prediction has been calculated by Neural Network Stock Trend Predictor NNSTP-2.
The chart shows S&P-500 index forecast for the period from January 10 to January 14, 2011. The possible ^GSPC behavior is a sideways fluctuation within 1% without significant advances. The prediction has been calculated using Neural Network Stock Trend Predictor NNSTP-2.
Chart represents S&P-500 index possible behavior for December 6-10, 2010. The forecast is a slight uptrend with a gradual reversing to a downtrend. The prediction has been performed using Investment Analyzer InvAn-4 (pattern similarity forecast).