The recommendation system works on an idea of suggesting or recommending items, products, books, movies, etc. by analyzing and using some filtering to find the user's interest. To maximize the growth of business and profit gain, users need to be recommended with products belonging to their area of interest. To fulfill this requirement, the recommendation system has been implemented. In this study, the discussion is over recommendation system and how different concepts come to work out individually as well as together for recommendation. In this analysis, the focus is on recommending the method of e-commerce. In that scenario, “cold start problem” comes into consideration. Cold start problems are also studied, and a purposed idea has also been highlighted to reduce cold start problem to some extent. ‘LCW Aspect' is going to execute and analyze user's culture, weather, local scarcity, and focused on solving recommendation problems for new emerging users.
TopIntroduction
Since last few decades, it has been observed that, the sheer information analysis is growing massively just like weeds in a field. The number of movies, web series, books, CD, and online products are seen to be getting uncountable day by day with rapid increase in their volume. This volume of amount and varieties in products is relatively very confusing for people to filter or to select the best which matches for them. People have to handle the information of their own effort and sometime get the good one. But many time customer or people not able to get the product of their own choices because either the product is not accessible or not visible to them. There is a lot number of things are done to filter, to give customer what they needed.
For example, newspaper editor selects what are the paper or article are most liked by people and accordingly put them or print them. Book keepers have to give effort of their own to decide what books to carry so that people would like them to buy. These take a great effort and time. However, the emergence of electronic information age, this barrier becomes less and makes easy to suggest everyone with less effort. With the help of information, now it is easy to recommend customer products, items of their choices and interests (Selvi & Sivasankar, 2019). The first paper on collaborative system was published in mid-1990, since then the Recommendation system has become able to fix a crucial role in Research Area (C. D. Wang et al., 2019).
The Recommendation system helps the user, customer and clients to select the items, products which are of that user’s interest. Basically, the Recommendation system works on two methods. The first one is “Content based” system and the second one is “Collaborating filtering” system. The content-based system works on the principle of user’s past purchased, likes, rating etc. The second Collaborating system works by suggesting users on the basis of similar preference (Tahmasebi et al., 2021). In today’s date, many e-commerce websites are being operating which are serving customized recommendation to user. Amazon.com is a great example of that. It recommends products, items, movies, web-series, books, kindle books etc. Like that, Netflix recommendation system suggests movies, web-series to users according to their past clicks, type of movies recently watched, and their area of interest in past (Nilashi et al., 2018).
Recent recommendation system basically works on the rating predictions, which are given by the customers when they buy and use any product. These rating may include (a) how many customers rated as good to any specific product (b) each user can able to rate only once (c) the data of rating should be static. However, these assumptions of rating may be violated at many scenarios. For example, it will violet the assumptions when a particular customer buy product in multiple purchases and given rating every time, these products includes food, grocery, daily needs items etc. Similarly, this also effects negatively in rating based recommendation system (Lv et al., 2019). The recommender system logically works on the past data of user, purchases, ratings etc. For example, if a customer buys or clicks or searches any product, then whenever that user again logins, then he would be given many recommendations related to that category or interest as shown in Figure 1.