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.

]]>- 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

]]>SMFT-1 consists of the tools that employ fundamental ratios rating model, technical analysis, chart pattern analysis, Elliott Wave theory, cycle analysis, candlesticks model, trend lines analysis, regression models, etc. The calculations are empowered by Neural Network. The implemented methods are statistically proven and widely used.

Most methods are provided with back-test calculation to estimate the accuracy of forecast within the recent performance period. The back-testing computations also may 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.

]]>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.

]]>After years of intensive development Addaptron Software has released Trading Decision Support System TraDeSS-1, advanced computer program for institutional traders and investors. It is a comprehensive and effective software to help finding the best trading opportunities, maximizing profitability using several predictive models with back-testing features, and optimizing algorithms by running simulations.

TraDeSS-1 is equipped with an advanced forecasting state-of-the-art system. The predicting can be done using nine forecast methods of different nature. Only one method, a combination of a few ones, or all together can be used. Each method is provided with back-test calculation to estimate the accuracy of forecast within the recent performance period. The back-testing computations play an important role if more than one method is selected. It allows assigning a weight to each method in a composed result; the weights are proportional to the ability of the methods to predict the price.

The comparative analysis of simulations shows that systems based on predicted entry-exit signals generate a better profit in around 70% cases than random-entry trading systems. As well as, it should be noted that a multi-model forecast provides a significant improvement over the best individual forecast. It can be explained by the existence of many different independent factors contributing to the error in each forecast which is normally distributed around an actual value.

Since sometimes predictions can fail, to preserve a capital amount in a volatile market, the software enables simulating different risk management approaches. Depending on the character of particular trading shares and the current market conditions some ideas can work better than others. To optimize the strategy in a particular case, the software enables testing different algorithm configurations and finding automatically the best ones. It is especially important for exit points to minimize losses (and ultimately maximize an overall profit). All optimizations can be done automatically by scanning 64 possible logical combinations and adjusting numerical parameters.

TraDeSS-1 has a functionality that allows estimating a hypothetical maximum possible profit in case of 100% accurate forecast. Although an actual forecast cannot be so accurate, this feature combined with comparative analysis enables discovering the best trading opportunities among different types of financial instruments. Calculating maximum theoretical return allows finding optimal buy and sell signals. Also it helps estimating a reasonable amount of initial investment at given transaction fee. Users can choose to re-invest each time a new or the same amount and see the difference in results.

The software has forward testing and assets management features. It allows monitoring the simulated or actual completed transactions, reflecting total trading activity, and evaluating the success of trading in overall. It enables working with many separate data files that is convenient in case of managing multiple assets and keeping the archives of older activities.

TraDeSS-1 has also a few independent tools, such as, technical indicators predictor, cycle analysis forecast, Neural Network (NN) forecast, fundamental 3-month rating model, etc. The detailed description is presented in User’s Manual (accessible from menu Help after downloading and installing the software). To download the software, the registration is required: http://www.addaptron.com/m/registr.php

]]>Fortunately, statistical methods combined with computer power can be a good solution to make the candlestick patterns recognition works less time-consuming and more effective. These days, Neural Network (NN) can help to automate a candlestick patterns recognition task. NN should be properly trained in order to be able to predict the next candlestick parameters with the highest probability. One of the obvious problems of implementing a candlestick pattern NN predicting system is a formalization of inputs.

Numerous tests show many possibilities of improving NN candlestick patterns recognition systems. For example, output result can be composed from selected optimized calculations based on different historical periods. Also there are many different ways to formalize the shapes and relative positions of candlesticks. As well as, as back- and forward-testing show, it is reasonable to re-train NN for each particular type of shares and latest historical periods to make the forecast more accurate.

**Optimal Solution.** There is an automated tool FTA-2 (free use of fully-functional version for one month). It has module which enables using Neural Network to recognize typical candlestick patterns and predict future prices (open, high, low, close). This module predicts only one next candlestick but the prediction can be successfully used for different widths of candlestick, i.e., the number of trading days in one candlestick. The module has been enhanced to calculate result that is composed from different historical periods that allows making the forecast more accurate. Also it can perform comparative forecast analysis for many symbols.

**Useful resources:**

- Candlestick basics – major signals
- Neural Network basics – introduction
- The computer program which enables using Neural Network to recognize typical candles patterns and predict future prices – software FTA-2

SAR indicator gives a strong signal when a price trend is about to reverse, therefore, this indicator can be used for prediction. To compare the predictive ability of SAR with other indicators, it has been implemented into the technical analysis module of Fundamental-Technical Analyzer FTA-2. SAR calculations have been used to collect statistics based on the forecast simulations for major indexes and ETFs during August-October 2011 period. As a result, SAR’s position was mostly in “top ten” indicators list.

*The research and presented chart are made by Fundamental-Technical Analyzer FTA-2, one of the software modules that enables composing Neural Network forecasts of many indicators with weights accordingly to each indicator’s predictive ability.*

Omitting logical rules for accelerating factor and reversal conditions, a recurring core formula for SAR is the following:

SAR (current point) = AF * [EP – SAR (previous point)] + SAR (previous point)

*where:
AF – Acceleration Factor (normally starts from 0.02 and increases by 0.02 if each next point reaches a new extreme, saturates until 0.2);
EP – Extreme Point (lowest low or highest high).*

To summarize, Parabolic SAR can be enriched by combining it with Neural Network and successfully used for predicting stock market prices. Combing it with Neural Network allows extracting more statistically stable patterns and, therefore, providing a better accuracy in the forecast. As simulations showed, improved results can be achieved if SAR is transformed into more sensitive indicator by subtracting it from close price (it indicates the degree of SAR and price convergence).

However, instead of assuming that waves obey only the sequence of Fibonacci, harmonic, or fractal ratios, a more general approach has been developed – the software takes into consideration all extracted waves. Due to employing Neural Network (NN) the module enables identifying both the price and date of extremes. The software has a flexibility in tuning and optimizing computing parameters by users. It allows choosing the number of counted waves in each case for NN training in a range within 9..24. Also one can set the amount of iterations for NN learning from 50 to 5,000.

]]>The statistical analysis of simulations shows that systems based on predicted entry-exit signals generate a better profit than random-entry trading systems. TFW-1 enables forecasts to increase a trading profit. The calculations are done on server-side by a robust artificial intelligence system. Since sometimes predictions can fail, to preserve capital in a volatile market, the software enables simulating different risk management approaches. TFW-1 simulation allows testing generated predictions combined with buy-sell signals.

Depending on the character of particular trading shares and current market condition, some ideas can work better than others. To optimize strategy for each particular case, the software enables testing a given idea and finding automatically the best set of algorithms. It is especially important for exit points to minimize losses and ultimately to maximize an overall profit. Some algorithms have customizable parameters that can also be optimized. All optimizations can be done either automatically by scanning 64 possible logical combinations and adjusting numerical parameters or manually.

TFW-1 allows monitoring the simulated or actual completed transactions, reflecting total trading activity, and evaluating the success of trading in overall by stand-alone computing. It enables working with many separate data files that is convenient in case of managing multiple assets and keeping the archives of older activities. You are welcome to download and use for free (during the first 30-day period) a fully-functional version of TFW-1.

]]>**About Expert Method.** Apparently, the more good forecasts are taken into consideration, the more precise can be an approximation to actual value. There is Expert Method. This method can be explained by following. As example, an experimentalist shows a pen and asks a group of about 40 people to write down their estimate of the length. Then he collects notes and calculates the average number – normally it is almost 100% accurate. Why it works? Because everyone makes errors in different directions so that averaging gives a precise result.

**The Details of Experiment.** To find an optimal number of top performing indicators, two tests have been done – using artificial data and real market data. Artificial data allow performing forward testing with more consistent statistics. Although back-testing has been done on out-of-sample sets, it did not have the same forward-testing success every time. Forward testing showed that in average few indicators might produce less accurate prediction than many.

*The researches and presented chart are made by Technical Analyzer TA-1 (the software is able to compose Neural Network forecasts of many indicators with weights accordingly to each indicator’s predictive ability).*

**Conclusion.** The main conclusion is that relying on a couple of best indicators might yields less consistent success over a long run than using many best and good ones. However, too many is another extreme and not good. The second conclusion is that the list of best indicators is not static – it evolves depending on many factors, including market conditions and, probably, on the number of traders employing particular indicators to make their buy-sell decisions. Thirdly, if the best current top of indicators is known, here is a magic number – it is around 30. And finally, better results are possible if indicators are combined accordingly to their latest back-testing ranking.