Smart Chatbot System for E-Commerce Assitance based on AIML

Abstract

Currently, the conventional market is starting to be replaced with many online markets. The tight online market competition demands excellent service from sellers to buyers, so many online stores provide full 24-hour service. This service certainly requires a lot of money if done manually. Chatbot can be used as a solution to automatically shop online. Then the bot must be able to provide an accurate and fast response. This study proposes an intelligent chatbot system based on Artificial Intelligence Markup Language (AIML) which can be used as an e-commerce assistant. This Chatbot is applied to the Telegram application. Input questions from users will be processed through three stages, namely, parsing, pattern matching and crawling data using AIML. In the AIML process, user requests are classified into three categories, namely general questions, calculations, and stock checks. Where the calculation request traps the order and payment process. Based on the results of 300 trials, the proposed method can answer all user requests well, with an average response time of 3.4 seconds.