The users helped by the search engine for online transactions in e-commerce; nonetheless, there is still a lack of search interest from the user and online shopping intentions. To boost the user's search for product recommendations, use a search engine for the quest but not for purchasing purposes. Existing frameworks have some significant problems in the recommendation technology, such as new product problems, fewer evaluation problems, a vast amount of data, etc. Many e-commerce applications lack a better search experience like an Exploratory search system. This research work aims to create a conceptual model for recommendation systems using exploratory search, to study the behavior of users and the efficacy of exploratory search in terms of the quality of the search results produced. Several machine learning algorithms are used in this research to classify e-commerce products and evaluate the performance of these algorithms. The full-text search mechanism is used to implement an exploratory search system. The exploratory search system is evaluated by three criteria called to look up, learn and investigate. After the experiments and evaluation, it is observed that AdaBoost over decision tree performs better than the other classification algorithms implemented. The exploratory search system satisfies the three requirements that are lookup learn and investigate during the search process. Contributions to this work are to build a conceptual model for the recommendation system through the dataset of user events and finding the implementation of an exploratory search mechanism in an e-commerce application. � 2020 Mohammed Mahmudur Rahman, Zulkifly Mohd Zaki, Najwa Hayaati Binti Mohd Alwi and Md. Monirul Islam.

The search engine assisted consumers with online transactions in e-commerce; yet, there is still a lack of user interest in searching and online purchasing goals. To improve the user's search for product recommendations, bring into play a search engine for the quest but not for purchasing purposes. Search engines facilitate users in locating desired information, while recommendation systems assist users in discovering more content that aligns with their preferences or provides suitable alternatives. However, with a mix of lookup, browsing, analysis, and exploration, exploratory search gradually focuses more on the user's needs and the accessible information to address them. Exploratory search is not enabled by general-purpose search engines, but it is supported in part by a few related applications. Similarly, the majority of review publications on Recommendation Systems (RS) focus on evaluating alternative suggestions, building algorithms, or taxonomies of already existing RS while ignoring other design difficulties. Most methods of recommender systems in the past did not take contextual information into account. The users' evaluation of RS is handled in general terms in the Xiao & Benbasat conceptual model and is viewed as the users' opinion of RS success. As a result of the research, three directions have been added to the conceptual model. First, this study is looking into users' evaluation attributes as moderating factors of the perceived quality of the RS outcome, i.e., perceived decision quality. Secondly, the proposed enlarged model is evaluated from the end-user perspective in the context of a cognitive model for search by analyzing the user's behavior and the success of exploratory search in terms of the quality of results produced by the search process. Thirdly, this work introduces a new variable on item availability. This research provides a software framework that allows us to investigate the model's dimensions and set up empirical tests to conduct experiments on the model as a whole. The proposed model intends to improve decision-making and increase user experiences and business outcomes in the e-commerce area by merging advanced machine learning techniques, user behavior analysis, and contextual data processing. The dataset included user events and the user experience data collection collected from the Kaggle platform provided by Expedia for this research experiment. The train dataset contains around 300 million records and the test dataset contains around 75 million records. In this research, the classification algorithms are chosen for the experiment and evaluation. The accuracy measurement, graph plotted by the accuracies determined by running the algorithm, classification report, confusion matrix, and Receiver Operator Characteristic (ROC) curve are all included in the method performance evaluation. These performance evaluation methodologies assist us in selecting the best classifier: AdaBoost over the Decision Tree algorithm, which has higher accuracy than other implemented algorithms. Extracting more functionality from the data regarding experiences would further enhance the recommendation framework. The full-text search mechanism is used to implement exploratory search system. The exploratory search system is evaluated by three criteria called look up, learn and investigate. After the experiments and evaluation, it is observed that AdaBoost over decision tree performs better than the other classification algorithms implemented. Finding new features and applying them to the dataset which results in a considerable change in the product class prediction outcomes. vii This research provides product recommendations based on consumer preferences, provide RS with the prospect of promoting and advancing the quality of consumer decisions.