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.

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.

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.

Cycle Analysis Forecast Gives Clues for March 2010 Stock Market Performance

According to cycle analysis forecast, SP-500 performance for March 2010 expected to be negative. The chart below has been plotted using Stock Market Analyzer-Predictor SMAP-3.



The stock market performance curve can be considered as a sum of the cyclical functions with different periods and amplitudes. It is not easy to analyze the repetition of typical patterns in stock market performance because cycles mask themselves - sometimes they overlap to form an abnormal extremum or offset to form a flat period. A simple chart analysis has a certain limit in identifying cycles.

Addaptron Software has developed Stock Market Analyzer-Predictor (SMAP), computer program, which is able not only to extract basic cycles of the stock market (indexes, sectors, or well-traded shares) but also to predict an optimal timing to buy or sell stocks. SMAP calculation mainly based on extracting basic cyclical functions with different periods, amplitudes, and phases from historical quote curve. To detect correctly major cycles, the historical price data are transformed from time domain to frequency domain (spectrum).

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

---

Nothing in this piece or on 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.

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

Stock Market Forecast Using Expert Method

The more methods and information are taken into consideration, the more precise an investment-related solution and, consequently, the more profitable is investing. There is Expert Method. This method can be explained by following. As example, an experimentalist shows a pen and asks 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? Everyone makes errors in different directions so that averaging gives a precise result.

There is a webpage where you are invited to build a collective forecast for S&P-500 index. Please share your opinion by voting and see the result of composite forecast. If you use more than one method, approach, or tool for prediction, it could be reasonable to give a vote for each one. All participants may benefit from building a simple average forecast. However, do not put too much trust in any method alone - make your own conclusion.

Link to S&P-500 index weekly forecast

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

SMAP-2/3 Update

Stock Market Analyzer-Predictor SMAP-2/3 has been added an option to specify the type of input data - adjusted quotes (it is useful when a stock splits) or actual quotes without adjusting. Also now SMAP-3 allows managing the list of symbols and performing a forecast comparative analysis. A user can edit, delete, add symbols on the list, and download all files. The processed symbols output is sorted according to expected performance. To update your tools, visit Addaptron Software download page or use Update interface button.

Addaptron Software Updated Stock Market Analyzer-Predictor

The stock market has powerful and consistent cycles. They can be as a bad surprise for some investors but others know how to take advantage of the market cycles. By identifying the cycles it is possible to anticipate tops and bottoms and to determine trends. The stock market cycles can be a good opportunity to maximize return on investments. "The stock market cycles known by investors for long," says Alex Shmatov, president and founder of Addaptron Software. "The stock market is an alive system - around can be joy or fear but its pulse always exists. And many investors benefit from a fluctuating nature of the market."

The presence of multiple cycles of different periods and magnitudes in conjunction with linear trends, can form a complex pattern of the stock market performance curve. Often cycles mask themselves - sometimes they overlap to form an abnormal extremum or offset to form a flat period. It is clear that a simple chart analysis has a certain limit in identifying cycles parameters and using them for predicting. SMAP-2 is able to extract basic cycles of the stock market (indexes, sectors, or well-traded shares). To build an extrapolation, SMAP-2 uses the following two-step approach: (1) applying spectral (time series) analysis to decompose the curve into basic functions, (2) composing these functions beyond the historical data. SMAP-2 also enables finding optimal timing to buy/sell by analyzing month of year, day of month, and day of week (the calculation is based on statistical analysis). The investors who empowered by using SMAP-2 are less likely to get fooled into buying at the worst time. SMAP-2 is one the most popular among investors software tools.

Addaptron Software develops and provides advanced data processing software tools to businesses and individuals who choose to improve efficiency of their decision-making. The company specialized in developing software that enables comprehensive data processing to extract meaningful and useful information in areas of investment, management, and marketing. One of the main approaches is to reflect precisely system's quality using mathematical modeling. Currently, the company provides software tools to investors to help them more effectively manage their investments.