What Is ASTA? The development of ASTA was instigated by a need for good working tools for the following research tasks: A Test Bench for Old and New Trading Strategies Many technical indicators for stock prediction are accepted and widely used, without ever having been subject to an objective scientific analysis with historical stock data. It is true, that many commercial software packages for technical analysis offer both a comprehensive programming language, and a simulation mode, where the performance can be computed. However, most available products do not take this task very seriously and real trading simulation with a multi-stock portfolio is seldom possible. Furthermore, often the performance measures are not sufficient for a serious evaluation of the behavior of an algorithm for a longer period of time. Therefore, there is a need for a scientific test bench for the methods and algorithms already developed and in common use. The need for proper evaluation of new trading algorithms is of course the same as for existing ones. ASTA is developed in MATLAB and therefore is suitable for tests of algorithms developed in the same language, but MATLAB can also communicate with other languages. An Interactive Development Tool for Trading Rules There are reasons to believe that a successful trading system consists of many disjunct parts, where a buy signal can be for example, "screened" by looking at the traded volume. A buy signal issued with a low traded volume may be then rejected. Other composite rules include looking at the general trend of the stock before accepting a signal from the system. ASTA provides the possibility to test such composite rules easily. The included function library and the possibility to define a trading strategy interactively, make implementation and evaluation of many trading strategies possible "without programming." A Non-interactive Development Tool for Trading Rules Even if the general look of the algorithm is fixed, there are often a lot of tunable parameters that affect the trading performance. Examples are filter coefficients, order of polynomials and levels above or below which an entity should pass in order to generate a trading signal. Since we believe that the actual behavior during a realistic trading situation is essential for proper selection and optimization of an algorithm, there is a need for an objective function that can be included in an optimization phase for parameter tuning. Furthermore, it is possible, to automate the development of trading rules. Since ASTA defines the trading strategy as symbolic Buy rules and Sell rules given as arguments to the system, it would be perfectly possible to construct buy and sell rules in a genetic framework, for example. Data Generation for Post Processing The comprehensive and user-friendly macro language in ASTA makes it a very suitable tool for extracting data for further analysis, such as classification with neural networks or fuzzy rule bases. A raw selection of trading situations is first set up with simple trading rules. Data ("features") for these situations is then automatically written to a file. A "target" value for each trade is also supplied. Thereafter it is a classification task to find out how to distinguish between a profitable trade andanon-profitable one, based on the given features.
http://www.cs.umu.se/~thomash/astahome 原来这个平台对做研究是免费提供的，但我发现的时候作者说正在商业化，不再免费提供。我曾去信给他套近乎，但没有回音。我看这个平台还是很不错的，那位大虾E语有功力可以再与作者套套近乎，或者能够搞到也未可知。[/u]
呵呵，谢谢hylt老大垂青，我这个人比较懒散，担任过的几个版主最后都溜号了。而且matlab我还不太熟，仅仅是准备学习。因此，可能我不太合适 我计划明年到美国去。象老大这样既懂股票，外语底子又好，对国内外证券软件又了如指掌的人，我觉得应该想办法把这个优势转化为money。有机会的话聊聊，看看能不能碰撞出什么火花