Product price prediction by machine learning method through web scrapping

Abstract

In this emerging world of the internet, there is lots of data present and retrieving this data becomes very complicated. As a result, web scraping is one of the important method of data gathering. Web scraping is a technique of extracting data from various websites and depending on the tool end-users can accessthe data in severalformats such as spreadsheet, csv, json, xml and database. Web scraping is used in many fields like e-commerce, market research,brandmonitoringand etc. Our system proposes amethod of fetchingproduct data from e-commerce websites and comparing them. For extracting data different tools are used such as Scrapy, BeautifulSoup, Selenium, etc. Our system uses Selenium for extracting data. After extraction data is stored into MySQL database. This data is then displayed in a comparable format on our webapp. Visiting websites one by one and comparing product details is time consuming, so to overcome this our system will display all the product details from various websites, which will help the end-user to compare the products. Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy. Prediction model is an information output generated by an ML algorithm trained on historical input data. A machine learning prediction is simply a model’s output when provided with an input. Reliable ML predictions offer valuable insights leadingto more confident and guided decisions by businesses. e.g.,Business sales forecast for the next quarter, Likelihood of customer churn for a specific brand, etc.