Integrating “Random Forest” with Indexing and Query Processing for Personalized Search

The internet has become an integral part of at least 4.4 billion lives. An average person looks at their device at least 20 times a day. One can only imagine the amount of queries a search engine gets on a daily basis. With the help of all the data acquired over the years, the internet updates us with all the biggest trends and live events happening all over the world. A search engine is able to provide query suggestions based on the number of times a keyword has been searched for or the current query relates to a certain trend. All these trends are updated to every device internationally or locally. This concept is generalized throughout all devices that use any kind of search engine on any application. Through this paper we intend to propose to use Random Forest as a predictive model to be integrated with the indexing process of the search engine to produce query suggestions that a user would want to search, contrary to the query suggestions that are usually displayed based on hyped trends and fashion.