International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 08 Issue: 09 | Sep 2021 www.irjet.net p-ISSN: 2395-0072 © 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1320 Traveler’s Guiding System Using Data Mining Techniques. Prof. Sagar Birje * Asst. Prof & HOD. Department of Computer Science & Engineering, Angadi Institute of Technology and, Management, Belagavi, India Pramod Patil 1 , Kshitija Desai 2 , Malatesh Patil 3 , Malaprabha Patil 4 Department of Computer Science & Engineering, Angadi Institute of Technology and Management, Belagavi, India ----------------------------------------------------------------------***--------------------------------------------------------------------- Abstract — Nowadays, Recommender Systems are being used in multiple different domains. The application recommends to a tourist the best attractions in a particular place according to his preferences, his profile and his appreciation to previous visited places. This paper proposes a hybrid recommender system that combines the three most known recommender methods which are: the collaborative filtering (CF), the content-based filtering (CB) and the demographic filtering (DF). In order to implement these recommender methods, we have applied different machine learning algorithms which are the K- nearest neighbors (K-NN) for both CB and CF and the decision tree for the DF. The hybridization is a good choice to make the best of their advantages and to overcome the cold start problem. To enhance the recommendation accuracy, we use two hybridization techniques : switching and weighted. Keyword- Recommendation, KNN clustering algorithm, Apriori classification algorithm, Content based filtering. I. INTRODUCTION Data mining is nothing but the process of identifying patterns in order to extract useful data from large datasets using methods of machine learning, statistics and database systems. As a huge amount of data get generated from various organizations websites, social media sites, etc. Hence it’s very essential to extract required data which will useful for taking future decisions. Sometimes past history/data becomes useful for future predications. Main goal of data mining process is to extract data from large datasets and convert it into understandable or useful format. Travelling is an important part of our life. [1] Hence planning of it is also important. Nowadays, lots of travel agencies are there which helps tourists to plan their vacations according to their packages. Hence, sometimes user’s needs to adjust their plans according to their agencies generalized plans. Lots of Websites provides us travelling options. Some websites helps us to plan our trips. They recommend us places if we specify a particular location. But these systems are more generalized and also they may suggest us same places repeatedly. In this paper, we propose to develop a new hybrid tourism rec- ommender systems that combines three recommender filtering methods (CF, CB and DF) while using two hybridization tech- niques: switching and weighted. For the weighted technique, we propose an automatic approach to set the weights’ values by applying a novel linear programming model II. EXISTING SYSTEM When we want to plan a trip for holidays or general visit, very first we take a help from travel agencies then we need to plan according to travel agencies. [2] But, because of this we face some difficulties like our vacation get start but travel agency package date is at the end of our holiday or in our working time. Existing system is generalized system, i.e. travelling recommendation might be same for some of tourists. It provides plans according to travel agencies, which is not match with tourists need and interest. Sometime travel agencies promises good quality service to tourist, but that does not happen actually and tourist face many problems. III. RECOMMENDATIONSYSTEM We propose a system in which tourist will define his/her interest, type of place in which user is really interested then system will provide some recommendations like best places to visit according to season, route, hotels, start time and end time, address, website(if available), reviews of other users, etc. based on his/her need, past history and interest. Then tourist will choose place and other things according to his/her need.Tourist will first need to fill the details then the system will analyze the data entered by tourist. These details will include information like users current location, distance range in Km and also types of places user is interested in. Here, user can choose multiple types of places. After this system will analyze data entered by user and will recommend the number of places which are within the specified range as well as which are of that specified type. After clicking on that particular place user will be able to view all the information about that place along with photos and reviews of that place. Also user can be able to view frequently visited places which are visited by most of the users even though it’s not within that specified range. Content-based filtering is used in review module of recommendation system. System takes the reviews in text format and generates the numeric value for each review. These numeric values get displayed in star ratings to the tourist users and these star ratings help the user to decide