ONLINE PLANT SALES RECOMMENDER SYSTEM USING MACHINE LEARNING
ABSTARCT :
In today's technical era, every startup or a company attempt to establish a better sort of communication between their Plants and the users, and for that purpose, they require a type of mechanism which can promote their plant effectively, and here the recommender system serves this motive. It is basically a filtering system that tries to predict and show the items that a user would like to purchase. By analyzing the preference of the users, companies can decide which plant to be launched in the market to procure more benefits. These systems are proved to be very beneficial in variety of domains involving music, books, movies, research articles and plants in common. In this paper, we review various mechanisms and techniques that are required for recommender systems for recommending the plants or items in the domain of fashion and books.
EXISTING SYSTEM :
• The recommended collaborative filtering recommendation (CF) by analysing existing user behaviours and information is widely used in the industry.
• For learning the weights of the embedding layers, collaborative filtering was the solution to find similar customers and plants, creating customers and plants embeddings learned from existing ratings.
• Deep learning techniques with different neural network architectures can be applied to the recommendation systems to identify the different patterns and behaviours of the customers in e-commerce applications.
DISADVANTAGE :
• The complex problems using unstructured data can be efficiently solved using different machine learning techniques.
• A huge amount of information is available on the internet, learners face the problem of searching for the right information and online recommendation system can solve the problem of information overload efficiently.
• It is observed that major problems in item-based RSs are the impact of context awareness, loss of neighbor transitivity, and sparsity.
• This method is useful for the formation of latent factors (predictions) in the scope of RSs to resolve the problems faced by the approach of collaborative filtering.
• Collaborative filtering is the most popular technique used for recommendation systems but the major drawback with this approach is its inability to solve the cold start problem.
PROPOSED SYSTEM :
• The basic goal of a recommendation system is to propose something new that meets the user’s wants or preferences for plants or information services.
• The proposed system depends on statistical analysis to solve the problem of a cold-start by providing a recommendation depending on the preferences matrix of the plants.
• The proposed system is a part of the commercial environment, which involves an e-commerce website, an e-bank system, and customers.
• The proposed RS system is employed on an e-commerce website that is a specialist in selling computers and their peripheral instruments, so it is possible to say that diversity and scalability problems are controlled.
• The main constraint is the lack of ratings among banking plants, but a proposed solution is using recommenders systems to segment and study the transactions of the customers for generating implicit ratings and offer the best possible plant for the customer.
ADVANTAGE :
• In many of the learning applications, the ratings are found very sparse and this causes collaborative based methods to reduce its performance in the recommendation.
• It is a type of neural network consisting of convolution layers capturing global and local computational characteristics to enhance efficiency and precision.
• The paper suggested a training regression model for several metrics that predict system performance based on a variety of parameters that characterize historical user activity in the system.
• These factors increase the amount of competition between global commercial sites, which increases the need to work efficiently to increase financial profits.
• In this field, many studies have appeared that suggest different ways to build recommendation systems that increase the efficiency of commercial sites.
• The collaborative filter (CF) is one of the most popular and frequently used recommender systems , and it is regarded as one of the most important components of successful E-commerce systems.
|