A RECOMMENDATION SYSTEM FOR PUBLIC SERVICE DOSSIERS

Abstract

Recommender systems are among the most popular applications of data science today. They are used to predict the "rating" or "preference" that a user would give to an item. Recommender systems are applied in many different fields such as ecommerce (online shopping), entertainment (movies, music, etc.), and education (recommend learning resources such as books, newspapers, etc.). Currently, in our country, almost all provinces and cities have online public service portals to facilitate the searching of administrative procedures and information dossiers. However, the amount of public administrative information is very large, making it difficult to find relevant procedures, dossiers and not really effective to meet the needs of users. This graduation thesis with the idea of building "A recommendation system for public service dossiers" to make it easier for users to look up and manage dossier information. Since, creating a public service dossier recommendation website using K-Nearest Neighbors (KNN) algorithm are experimentally studied and evaluated on real dossier dataset. The system is managed by SQLite database management system, python programming language, back-end uses Django and Django REST framework, front-end uses Vue.js framework to make web programming faster and more convenient. The result of this study is a recommendation system for public service documents /dossiers that helps users to search for procedures, dossiers by keyword and create a list of recommendations based on keywords, related information of users. Just like citizens, in addition to looking up and submitting the dossiers, administrative staff also receive, process and deliver the results of the dossiers via the online public service page to users. The system has simplified the search operation and enhances the efficiency of the implementation of online administrative procedures. Experimental results show that with the aims of the study, it will be possible to develop further to be able to integrate this solution into the current large--scale online public service websites to meet the usage needs of all organizations and individuals.