شماره مدرك :
6609
شماره راهنما :
6160
پديد آورنده :
اسدي، شاهرخ
عنوان :

طراحي يك سيستم هوشمند جديد جهت معاملات در بازار سهام با رويكرد داده كاوي

مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
سيستم هاي اقتصادي و اجتماعي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده صنايع و سيستم ها
سال دفاع :
1390
صفحه شمار :
پانزده، 117ص.: مصور، جدول، نمودار
يادداشت :
ص.ع. به فارسي و انگليسي
استاد راهنما :
رضا حجازي
توصيفگر ها :
سيستم هاي فازي-ژنتيك , فيلتر سازي نويز , خوشه بندي داده ها , رگرسيون گام به گام
تاريخ نمايه سازي :
30/1/91
استاد داور :
مهدي بيجاري، فريماه مخاطب رفيعي
تاريخ ورود اطلاعات :
1396/10/12
كتابنامه :
كتابنامه
رشته تحصيلي :
صنايع و سيستم ها
دانشكده :
مهندسي صنايع و سيستم ها
كد ايرانداك :
ID6160
چكيده فارسي :
به فارسي و انگليسي: قابل رويت در نسخه ديجيتالي
چكيده انگليسي :
A New Intelligent System for Trading in Stock Market with Data Mining Approach Shahrokh Asadi s asadi@in iut ac ir Date of Submission 2011 09 14 Department of Industrial Systems Engineering IsfahanUniversity of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Seyed Reza Hejazi rehejazi@cc iut ac irAbstract The stock market has always been an attractive area for researchers since no method has been found yetto predict the stock price behavior precisely Due to its high rate of uncertainty and volatility it carries ahigher risk than any other investment area thus the stock price behavior is difficult to simulation For years conventional tools have been developed but they have succeeded partially or have completely failed to dealwith the nonlinear and complex behavior of stock price so developing appropriate intelligent tools toestimate the behavior of stock price is needed This research presents a data mining based fuzzy intelligentsystem DFIS approach to estimate behavior of stock price Data mining is used in three stages to reducethe complexity of the whole data space At first noise filtering is used in order to make our raw data cleanand smooth Variable selection is second stage we use stepwise regression analysis to choose the keyvariables been considered in the model In the third stage K means is used to divide the data into sub populations in order to decrease effects of noise and rebate complexity of the patterns At next stage extraction of Mamdani type fuzzy rule based system will be carried out for each cluster by means of geneticalgorithm We use binary genetic algorithm to rule filtering to remove the redundant rules in order to solveover learning phenomenon In the following we utilize the genetic tuning process to slightly adjust the shapeof the membership functions Last stage is testing performance of tool and adjusts parameters This is the firststudy on using an approximate fuzzy rule base system and evolutionary strategy with the ability of extractingthe whole knowledge base of fuzzy expert system for stock price forecasting problems The superiority andapplicability of DFIS is shown for International Business Machines Corporation IBM and compared theoutcome with the results of the other methods Results with MAPE metric and non parametric test indicatethat DFIS provides more accuracy and outperforms all previous methods so it can be considered as asuperior tool for stock price forecasting problems Keywords Stock Price Forecasting Genetic Fuzzy Systen Noise Filtering StepwiseRegression Data Clustering
استاد راهنما :
رضا حجازي
استاد داور :
مهدي بيجاري، فريماه مخاطب رفيعي
لينک به اين مدرک :

بازگشت