证券市场不仅是国家经济的“晴雨表”，更是企业融资和广大股民投资的重要手段，对证券的预测分析无论对散户投资者、企业还是政府相关政策的制定都具有重大的理论与现实意义。

数据挖掘研究如何从大量的数据中获取对决策有帮助的知识。随着证券市场的不断发展，在证券信息数据库中积累了大量的历史数据，如何充分利用这些数据探寻证券市场自身的规律，成为人们关心的问题。

本文围绕证券预测分析，以通过数据挖掘寻找证券数据背后隐藏的信息，辅助投资者决策支持为主要目标，主要的研究内容和工作包括：

(1)关联规则挖掘

本文使用Apriori算法挖掘股票交易的关联规则，本文挖掘得到的关联规则包括股票间关联规则、含时间约束的股票间关联规则和股票交易时间序列关联规则三类。

(2)离群点挖掘

本文通过挖掘股票行情时间序列数据库中的离群点，发现股票的走势有自身的规律，局部的行情走势会重复出现。

(3)股票行情预测分析

本文将股票中的价格时间序列转换为涨幅时间序列进行分析，将股票的行情预测问题转化为分类问题，并使用k最近邻算法（KNN）进行股票的价格趋势预测。

(4)证券行情预测系统

Security market is not only a barometer in national economy, but also one of the most important investment tools for each person and financing means for enterprises. If we can make some prediction and analysis ahead of time, this would make significantly theory contribution and real meaning for no matter who like private investor, enterprises and the government policy maker.

Data mining aims to get previously unknown and potentially useful knowledge from a large amount of data to offer decision support. With the development of the security market, lots of history exchange data has been stored in database. It attracts more and more attention that how to use these history exchange data to discover the rules of the security market.

This paper focuses on the security prediction analysis, aims to get the hidden knowledge of the security data to assist investors to make decisions by data mining. The contents of the study are as follows:

(1)Association rules mining

This paper used Apriori algorithm mining association rules among stocks. The association rules mined in this paper includes stock association rules, stock association rules with time constraints and association rules of time series of stock transactions.

(2)Outlier mining

This paper mined the outlier of the stock exchange time series database, the result indicated that the local trend of stock would repeat.

(3)Stock price tendency prediction

In this paper, we converted the stock price time series into a variable rate of change in prices of the time series analysis, and predicted stock price tendency by classification. This paper used k-nearest neighbor algorithm (KNN) to predict stock price tendency.

(4)Security quotes prediction system