The Power of Using Multi-model Forecast in Stock Market

A multi-model forecast provides a significant improvement over the best individual forecast. It can be explained by existence of many different independent factors contributing to the error in each forecast which distributed around actual value.

Today, airplanes are equipped with a few different altimeters – barometric altimeter, radar altimeter, and GPS. Not to mention, pilots also use a visual estimation of altitude. Why do we need to use so many measurement tools? The first reason is that any of them can fail. There is another reason why multiple measurements are used everywhere – it is accuracy. For example, many different methods are used in weather forecasting to improve the accuracy of forecast.

The phenomenon of multiple forecast improvement can be compared with Expert Method. This method can be illustrated by the following. As example, an experimentalist shows a pen and asks a group of several people to write down their estimate of the length. Then he collects notes and calculates the average number – normally it is almost a precise result. Why it works? Because everyone makes errors in different directions so that averaging self-compensates erroneous deviations.

Concerning the stock market forecast, as experiments show, a multi-model forecast provides a significant (10-25%) improvement over the best individual forecast. Also tests show the advantage of using information even from multiple forecasts of different quality. That is because there are many different independent factors contributing to the error in each forecast and the results from different models are normally distributed around actual value.

Evidently, the methods should be different by their nature. Traditionally, fundamental factors and technical analysis are the major stock market tools. Within technical analysis, there are several different models: technical indicators, chart pattern analysis, Elliott Wave theory, cycle analysis, candlesticks model, trend lines analysis, regression models, etc. Most of these methods are statistically proven and widely used that often create self-fulfilling results.

As a rule, learning and also correctly using many of technical analysis methods may require a lot of time, especially, in a modern dynamic trading environment. Fortunately, the forecast methods combined with computer power have become a good solution to make the works less time-consuming and more effective. Except different linear and non-linear solvers and analytical methods, these days, Neural Network (NN) can help to automate a lot of computational tasks. A properly trained NN may enable predictions to the highest accuracy.

However, implementing NN application can be difficult for non-experts. Besides, one of the big obstacles of implementing NN predicting system is a formalization of inputs. Luckily, there are some software tools that already well-developed and do not require a deep technical understanding. These tools are optimized for each method and users might not notice even all computational power behind the buttons, windows, and charts.

Useful resources:

• Candlestick basics – major signals
• Neural Network basics – introduction
• The download page for computer programs that enable using Neural Network to automate many methods of technical analysis and predict future prices – stock market software tools

Transforming Moving Average From Lagging To Leading Indicator

Traditionally in technical analysis, chartists consider moving average indicators as lagging ones. In other words, these indicators are able only to confirm long-term trends that already started but not to predict in advance. The difference between simple moving average (SMA) and exponential moving average (EMA) is not so big in that respect although exponential one assigns more weights to the latest points and, therefore, EMA is more sensitive to the latest changes.

A more “predictive” signal can provide a combination of EMA with crossing price curve. Normally, it is used as an affirmation of increase in momentum but, still, the disadvantage of using this combination is that a significant move may have already happened. Therefore, if the trend is not going to last long, traders risk to enter a position too late.

Recent research showed that the predictive abilities of some well-known indicators can be improved by an additional transformation. Briefly, if an indicator is trend-differentially coupled with price – it demonstrates better predictive abilities than a simple indicator. As experiments showed – a similar improvement occurred when EMA indicator has been transformed to a slope of line and differentially-coupled with a price line slope.

The image below shows EMA divergence indicator forecast by Technical Analyzer TA-1. This interface represents one of three major modules of TA-1. The module provides with more than 50 popular technical indicators. Except chart analysis, indicators can be used as input for Neural Network to build 10-day price forecast. There is an option to compose forecast from all indicators – each indicator’s forecast is added with the weight proportionally to the current ability of the indicator to predict prices.

New Trading Decision Support Systems Group on LinkedIn

The new group Trading Decision Support Systems is intended to be a resource for individual/institutional traders/investors and software developers in stock market area to share ideas, initiate and participate discussions, benefit from the collective intelligence, and to expand network. It will be primarily focused on such topics as:

• Trading EOD and intraday different asset classes: trading tips, strategies, why, how, and results.
• Trading systems: algorithms, methods, technologies, human factor, and statistics.
• Software tools to support traders decisions: forecast methods, simulations, back-testing, and optimization.
• Technical Analysis: indicators and chart patterns.
• Fundamental Analysis: financial ratios and predictive models.
• News: analysis and formalization by converting to measurable variables to automate systems with contributing news factor.
• Numerical methods, data processing, artificial intelligence, and modeling in stock market areas.

Many things remain unchangeable in a trading world – supply-demand price balance, greed-fear driven mistakes, as well as, ability to think, make right decisions, and find the best solutions. When once winning approaches, strategies, or methods failed, many traders are prone to analyze the reasons why it happened. Then they create new approaches and develop new successful systems. If systems are automated, it is easy and fast to test them, collect and analyze back-testing and live statistics, and then make necessary improvements. That is why it is important to implement the best ideas in software applications that can be also used by others.

The computational technologies are changing. Systems empowered by Artificial Intelligence have self-learning abilities that enable them to adapt to market changes. One of the purposes of this group is to bring together the developers of decision support software and traders-users for mutual benefits: the developers get more ideas about their products’ improvements and make a better progress in developing software for traders, the users arise issues relating to their needs and wants. Hopefully everyone will find something useful participating in this group.

You are welcome to join this newly created networking group. Be the first to start a relevant discussion, promote your product or service. Please join Trading Decision Support Systems group on LinkedIn!

The Stock Market Is Likely Taking Summer Break

S&P-500 Index Drop from May 2 to June 8, 2011

Major stock market indexes slowly went down during the last several weeks, from May 2 to June 8, 2011. Since this decline has already broken a few important technical chart levels, many technical analysts believe that the trend might continue with sideways moves for a few weeks ahead.

Except seasonal reason, this May stock market decline was also caused by fundamental factors. The US corporate profits in the first quarter dropped for the first time in more than two years. The US unemployment rate in May increased from 9.0% to 9.1%. It looks likely that investors overreacted to strong corporate earnings at the beginning of this year. Economists believe that the government stimulus money could have artificially inflated the market. Evidently, without additional money injection the US economy would undergo a transition to a self-sustaining recovery.

From the fundamental point of view it is not clear how precisely the ending of stimulus is reflected in the current market evaluation. So that when the bond-buying program ends at the end of June, the US stock market might reach a more accurate equilibrium. Other surprises might be brought by the second quarter reporting season.

February Is the Month of a Slight Correction

With positive US earnings forecast for this year, 2011 is set to be one of the best years after the recession. Additionally, it is a good stock market timing of the presidential election cycle. According to many experts, this bull market will have more room to run. On the negative side, the US economy still remains too weak to help a high unemployment rate. Although the economy is improving, it is a slow recovery. Besides, this year the US government’s deficit might surge to a record $1.5 trillion.

S&P-500 reached a 2.5-year high level and now there is no much pressure to push the market down. However, bad economic or market-related news might easily cause a short-term correction. Another trigger could be a continuing downtrend of Indian Market that is currently already at a several-month low level. From the technical analysis view, according to the last 10-year S&P-500 statistics, February is the month of a slight correction.

Chart shows 10-year S&P-500 index statistics of monthly performance (calculated by Stock Market Predictor SMAP-3)

About Investment Analyzer InvAn

A good investing decision should be based on a multi-dimensional consideration of many criteria. However, making decision on the basis of too large data volume is not easy. To solve this dilemma, Addaptron has developed Investment Analyzer InvAn (IA) that performs fundamental, technical, and timing analyses converting them into three ratings. Then IA combines these ratings into a single number, composite rating, using a special algorithm.

IA fundamental analysis is performed on the basis of several key ratios and parameters (factors) to reflect company and its stock actual state and dynamics. Also it includes stock performance expectations on the basis of analysts’ opinion and external ratings. IA technical analysis rating is a result of processing the signals from tens of technical indicators and combining them into a single number by using Artificial Neural Networks (ANN) algorithm that allows reaching the best accuracy in the forecast. IA timing rating defines optimal time of a stock to be bought (sold) in the current stock market conditions.

Due to a fast and automatic data processing, IA enables watching hundreds of stocks. IA composite rating allows ranking stocks (stock comparison) daily from the worst to the best. It also has other useful features, such as, calculating optimal cash reserve. It can forecast stocks’ portfolios or an individual stock (index) on the basis of Fourier series analysis or using pattern similarity. It has also a filter to select stocks with Cup-With-Handle pattern, as well as, correlation analysis tool for advanced portfolio management.

IA helps investors pick the right stocks for their portfolio and determine optimal investment timing. It increases the speed and depth of analysis, makes most necessary calculations for investors, and maximizes profitability. IA is a comprehensive system with user-friendly interfaces that is easy to use.

The main purpose of IA is to provide users with in-depth analysis to maximize the return on their investments. IA has been tested for many years with excellent results; however, it has its own limit as any other tool. According to Efficient Markets approach, news and other public information are incorporated into the price of a stock with a certain time delay (price is supposed to reach and keep a stable equilibrium that change only each time a relevant new information is known). Since IA does not formalize all informational universes, monitoring companies’ news and macroeconomic trends are very important.

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