New Software Stock Market Tools SMT1:

discover the power of AI Stock Market forecast and trading simulation
- increase your trading profitability

2010-03-26

Neural Network vs. Cycle Analysis to Predict the Stock Market

Many stock market experts consider that the last several years show the increasing of general market influence on the behavior of an individual stock. You could find the number around 40% for stock market risk-factor in old books. But now the general market influence is considered almost 85%. That is why it is very important to look at the stock market first and try to predict it before investing in any stock nowadays.

The stock market can be presented by S&P-500 index. It is possible to build its different statistical forecasts using historical data. The purpose of the research was to compare two statistical methods: one that based on Cycle Analysis, another - on Neural Network. We used price and volume data to train this particular Neural Network.

A picture below shows how actual 5-day performance (yellow line) differ from predicted performances by these two methods. The top half is the comparison of Neural Network prediction, bottom half - Cycle Analysis. Green bars mean buy signals, red - sell.



Three major conclusions:
1. Cycle Analysis prediction gives signals too early, Neural Network prediction - too late.
2. In average, Cycle Analysis prediction showed slightly better accuracy than Neural Network prediction for the last six months (from June 2009 to January 2010).
3. It it possible to get a superior prediction by combining these two methods.



The links where the models' descriptions can be found:
Cycle Analysis
Neural Network




© Alex Shmatov. Published with permission of the copyright owner. Further reproduction strictly prohibited without permission.


2010-03-15

Spring 2010: A Short-term Outlook for Stock Market Is Positive

Retailers and consumer discretionary stocks demonstrate a strong performance. Retail sales posted a surprising increase in February (sales rose 0.3%). Although some analysts doubt that the spending gains can be sustained since the unemployment rate still remains high (9.7% in February), fundamentals of many companies gradually started showing improvements.

If the overall US national debt over the next few years rises to 100% of the gross domestic product, it will be alarming signal for the International Monetary Fund and international markets. However, many economists believe that US will be able at least keep the national debt stable relative to the size of the economy.

More positive news:
Recovery hope
It is still manageable at the current level of US federal budget deficit

...and negative ones:
Congressional estimates
Dead Cat
Death of American Capitalism
Wall Street Loses
US debt will keep growing even with recovery


Nothing in this piece or in this blog should be construed as investment advice in any way. Always do your own research or/and consult a qualified investment advisor. It is wise to analyze data from multiple sources and draw your own conclusions based on the soundest principles. Be aware of the risks involved in stock investments.

2010-03-01

Neural Network Forecast for March 2010 Stock Market Performance

According to neural network forecast, SP-500 price behavior for March 2010 expected to be fluctuating without significant advances. The chart below has been calculated using Neural Network Stock Trend Predictor NNSTP-2.



Neural networks can discover patterns in data that humans might not notice and successfully predict the future trend. Addaptron Software has developed NNSTP-2, neural network computer tool, to help stock traders in predicting stock prices for short terms. NNSTP-2 predicts future share prices or their percentage changes (can be chosen in settings menu) using Fuzzy Neural Network (FNN). Input data are weighted closing price of the stock and the volume traded (EOD csv-files). It operates automatically when creating the FNN, training it, and mapping to classify a new input vector. NNSTP-2 has a user-friendly easy-to-use interface. Historical stock price data are downloaded automatically from the Internet free-of-charge (US and worldwide stock exchanges). The software is intended for traders with a basic knowledge in stock analysis.

See also:
Weekly stock market forecast
Tools to predict stock market



Nothing in this piece or in this blog should be construed as investment advice in any way. Always do your own research or/and consult a qualified investment advisor. It is wise to analyze data from multiple sources and draw your own conclusions based on the soundest principles. Be aware of the risks involved in stock investments.