Abstract
Education has become very important in today’s era. Every year number of students pursuing Higher Education is increasing and United State of America gives these students a good opportunity to pursue their dreams. Students are attracted to America as it provides best education in the world, but there is little they know about the universities, ranking, living condition in America. To research about universities students perform number of ways as researching on Google, posting questions on forums, getting help from consultancy, asking friends, seniors, family. These methods are slow and unreliable. A friend can give biased opinion about a university if he has been there or simply because he does not know other universities well. A consultancy can also give biased opinion regarding a university if they have a tie up with that university. Other sources like Google take long time to research and you only get partial information. There are websites which provide similar functionalities such as www.internationalstudent.com and US news, but they don’t have detailed information as orientation of university, acceptance rate and surrounding conditions of university. This motivated me to provide these international students a way to research about university’s academic & surrounding condition and make the decision accordingly. This project is implemented using different techniques of data mining and data warehouse. It is based on datasets such as university, crime, transit, rent per room and weather which are collected from government official websites. Some research was needed in order to complete the dataset and start the project. The method used for data mining are data preprocessing, cleaning data and for data warehouse, the methods are data integration, OLAP operation. Using WEKA tool, a machine learning tool which is used for data mining and knowledge discovery, the data was cleaned, unused fields were removed and dealt with missing attributes. Other than this, the missing values were also manually researched and entered into datasets. To integrate all the datasets, snowflake database schema was used creating fact table and dimension tables. This was done using cube query of OLAP operation. This project is implemented using popular tier of LAMP (Linux Apache MySQL and PHP), data integration and OLAP technology which made application more dynamic and interactive. In this project, user will be able to search universities on the basis of state, their GRE or TOEFL score, orientation of university such as teaching or research and degree level. After applying filters, result page will display all the universities satisfying search criteria where they can add their favorite universities to wish list by logging in to application. The compare page shows all universities they have added to wish list. On compare page, user can compare universities by academic standing such as tuition fee, orientation, highest degree level and surrounding conditions such as yearly weather report, crime rate, transit facilities and rent per room by clicking on the row so that the popup will display all this information. There is Visas page where user can view non-immigrant visa types and information regarding that. Finally, there is Forums page for students to posts questions for fellow students. This project is enterprise level application which will be applicable for all universities in the US but due to time limitation, the focus is on California universities. The future work for this project can be extended to other states. Users of this project will be international students applying for universities in the US. The objective of this web application is to provide international students a guide to research about universities according to the degree level, tuition fees, ranking, climate conditions of area, average rent for rental houses, regional transits and crime statistics near the university area.