Stock price prediction is the act of trying to determine the future value of a company stock or other financial instrument traded on a financial exchange. Some researchers believe that stock price movements are governed by the random walk hypothesis and thus are unpredictable. Others disagree and those with this viewpoint possess a myriad of methods and technologies which purportedly allow them to gain future price information.
Well, obviously the dDM founder is one of them who believe in the possibility of building successful forecasting systems - otherwise Stock Price Prediction wouldn't be a topic here. In dDM we make advantage of technological methods in order to build forecasting models. We focus on machine learning algorithms to discover and extract valuable patterns that might be useful to predict the future stock development.
In 2005, we start our work motivated by the extensive textbook by Thorsten Poddig that introduces the basics of stock price prediction. Poddig presents the necessary fundamentals and typical methods in a comprehensive manner. Furthermore, the book  covers nature inspired techniques such as neural networks and genetic algorithms that became very popular in the late 90's.
In 2006, our first study of stock price prediction was successfully finished. We used a popular combination of Artificial Neural Networks and Genetic Algorithms in order to build forecasting models for the German Stock Market and Dow Jones index. Because of our promising results  we decided to continue our efforts in this research area.
In 2008, we came to the conclusion that it would be more efficient to use a standard machine learning software instead of implementing our own approaches as we had done before. We've took advantage of the very popular LibSVM framework and published a related study about the usage of Support Vector Machines  in the field of Stock Price Prediction. Support vector machines overcome the typical neural network problem of high computational complexity. The resulting forecasts are equally impressive even though the necessary computational costs can be decreased significantly.
In 2009, we extended our studies by using various learning algorithms in order to determine there ability for stock price prediction. We started using the data mining suite RapidMiner that provides various machine learning methods for data analysis purposes. The RapidMinder uses a comfortable plug-in mechanism to easily add new developed algorithms. This flexibility and the processing power of BOINC is an ideal foundation for scientific distributed Data Mining.