Addaptron Software is pleased to announce the release of a new 2013.05 version of Stock Market Forecast Tools SMFT-1. It is an integrated system that includes three major programs: the most popular software program SMAP-3 for stock market cycles analysis and forecast, NNSTP – Neural Network Stock Trend Predictor, and FTA-2 – a modified version of InvAn-4 that is a comprehensive tool used by serious investors for years. The new version includes several improvements, such as, models optimization, ability to read more different input file formats, and optional feature to enable a free Downloader.
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.
Candlestick patterns can signal a trend continuation or reversal. Many traders and investors know how to benefit from candlesticks analysis. As a rule, a simple chart analysis is used that requires analysts to remember and correctly interpret, at least, typical candlestick patterns. However, the number of possible different candlestick shapes and their combinations in a row can be huge. Besides, some patterns interpretations might be considered as contradictory or doubtful.
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.
- 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
Different chart patterns including candlesticks have been known in technical analysis for long. Now many of them considered as typical or classical ones. These patterns can signal a particular bullish or bear trend. Naturally, the signals are not successful all the time but give at least the most probable scenario of price movement. On the other hand, many other patterns have not been described yet. However, whether these patterns are known or unknown, many of them can be repeatable in the future and, therefore, they all can be used for prediction in the stock market.
To facilitate the job to memorize many different patterns and analyze a huge amount of charts, some chartists use special software tools – pattern recognition systems. These tools normally perform statistical analysis and filtration assuming that the patterns are generated by a probabilistic system and can be persistent in the future. The statistical researches of charts also show that indeed many formed patterns have typical structures of price developments.
Technical Analyzer TA-1 (TA) by Addaptron Software has a feature to predict a future trend of stock, ETF, or index prices using pattern similarity filters. The prediction period can be chosen within a range 1..60 trading days; the period of historical data that used for matching is recommended in 4..16 times longer than prediction period. TA searches for the best matches by scanning all historical data from the internal database. The typical number of scanned patterns is around 200,000 (if the number of symbols in the database is around 500).
TA ranks all possible matches on the basis of maximum correlation and minimum deviation within given historical period. It performs pattern matching using open, high, low, and close prices and volume data. When scanning is completed, depending on degree of similarity, TA ranks all possible matches within given historical period and then combine them into a single structure. TA composes forecast using several best matched patterns (top ranked). Since the statistical regularities of the patterns help to create more stable picture, TA allows adding up many top-rated patterns. The composite result is built as a weighted average with weights that are proportional to patterns’ ranks.
To try free version of TA, visit Addaptron Software download page to download and install it.
The two charts below show a possible behavior of S&P-500 index for the next week, April 18 – 22, 2011. The first chart is neural network forecast, the second chart is pattern similarity forecast. Both methods predict sideways fluctuations with an overall slight uptrend.