Design And Implementation Of Preference Based Educational Recommendation System

The growth in the usage of Internet has given birth to information overload. Tons of resources are available online on any topic. The variety of different resources makes it very difficult for user to find the relevant information source, hence it is a difficult and time consuming task.Online education is a paradigm shift of former way of learning. Users have flexible learning virtual environment to learn at own pace but user needs to spend a huge amount of time in hunting for a relevant resource which they are looking for due to the incapability of our search engines/recommendations systems and rare availability of an educational network which could be a one stop resource for any knowledge seeker. Along with this current online learning options are not interactive, easy to adapt and fun to learn due to which user loses interest very quickly.In today’s world, please spend most of their time on social networks which generally use collaborative filtering, content filtering or hybrid systems to recommend items to the users that are consistent with their choices and previous browsing patterns. Earlier approaches gauge the importance of the content by calculating relevancy score for a particular user. The users are served with the item with maximum score in the recommendation system eco-system. The scoring system encompasses multiple attributes for calculating the scores which are different for different contexts. For example, social networks would use users’closeness and previous browsing patterns as vital attributes in calculating score where as other general recommender system may use similar users based on common factor such as location, education, privacy settings of the content, creation time, degree of closeness with the other user, etc. browsing patterns as the vital attribute in generating recommendations. Another important aspect pertaining to the recommender systems is the cold start problem where the lack or sparseness of data becomes a bottleneck for the recommender system.This study proposes an online education system which has the collaborative, sharing, ranking and recommending features of today’s social networks. The structure of recommendation is based on user preferences. The user signup wizard is design to get more and more information from user when he signs up. Similar users based on preferences are calculated by the system and user is added to different groups based on it. Weightage of all the resources in the similar user group is calculated and based on the highest score the resources are recommended to the user. This study also aims in addressing the cold start problem by recommending latest trends to the user and learning from his behavior towards different recommendations, if user preferences are not set. Keen consideration has been taken while designing the user interface of such a system as the degree of success or failure in most of the online resources rely on the shoulders of its user interface. The only way a user can interact with system, due to this reason User Interface is considered as its heart. The quality of system relies on its easy to use, understand and interactive User Interface which is completely customizable as per user requirements and is readily adaptable by user of any skillset. It has been designed in such a way that it increases the efficiency of user by reducing his load of going through each resource and find out an appropriate result. But it also leverages users with multiple results related to his preferences and relevant to what he is looking for so a user can find a useful resource in no time which leads in increased productivity. This is a paradigm shift for the former way of online learning and is a master piece of technology which would take online education to next level.