STACK OVERFLOW: CROWD SOURCING RECOMMENDER SYSTEM

Abstract

The objective ofthis project is to develop a recommender system with help ofmachine learning algorithms. The recommender system will be able to recommend jobs itself by comparing tags ofthe user present in the dataset. This report explores techniques used or involved in designing recommender system. Different stages involving data pre-processing stage, data cleaning and database design will be studied and discussed. Finally the end product will be the obviously the recommender system which will recommend jobs which is basically the main functionality and we students will try to integrate it with user friendly interface or will develop a website which will be our secondary task. This project uses the Machine learning technique (binary classification) to develop the system. The main advantage of using this technique is that it provides the result by simply calculating its probability of occurrence. The system first checks the user field of interest (from the dump dataset of stack overflow) that in which field he is answering the questions most in stack overflow then the system will automatically recommend the job that are present in our dataset and displays to the user