Essay On Data Mining

804 Words2 Pages

The key objective in any data mining activity is to find as many unsuspected relationships between obtained data sets as possible to be able to achieve a better understanding on how the data and its relationships are useful to the data owner. The potential of knowledge discovery using data mining is huge and data mining has been applied in many different knowledge areas such as in large corporations to optimize their marketing strategies or even to smaller scale in medicinal research where data mining is used to find the relationship patient’s data with the corresponding medicinal prescription and symptoms. The various uses of data mining even extends to the possible forecasting of stock market for business analyst or investors in determining whether or not it is possible to combine 6 methods of analysing stocks and use them to automatically generate a prediction in increase or decrease of stock market prices by the end of the day. (K. Senthamarai Kannan et al, 2010) In his research paper, Kannan describes the use of the following 5 methods of analysing stocks. Among the methods described in the referred documentation were: • Typical Price • Chaikin Money Flow Indicator • Stochastic Momentum Index • Relative Strength Index • Bollienger Bands • Moving Average Kannan et al, 2010 predicts that by using the advantages of all the algorithms of the above, the buy and sell signal can be produced by using the Bollinger signal function. The Moving Average Crossover was used as a benchmark to determine how much effective is the new, combined technique as compared to the other methods. In his results, he documented that the profitable signal for Moving Average was 52.62% and that the new algorithm have a profitable signal of approximately 5... ... middle of paper ... ...ws the decision tree of MECE. Another article entitled: A Review: Application of Data Mining Tools for Stock Market by Kerti S. Mahajan et al, made a thorough review regarding the use of data mining tools such as decision trees, neural networks, association rules, clustering and factor analysis. In one of their excerpts, it is said that decision tree is an excellent tool for making financial or number based decisions where a number of complex information have to be taken into account. This statement further supports Qasem et al’s reasoning in using decision trees as a more suitable methodology to perform stock market analysis. Decision trees can also help in forming accurate and balanced picture of the risks and rewards involved that will particularly be a great interest to investors in finding out what the right time to buy is and how to find the right stocks.

Open Document