E-Negotiator Chatbot for E-commerce Websites

Project Title

E-Negotiator Chatbot for E-commerce Websites

Project Area of Specialization Artificial IntelligenceProject Summary

Negotiation is a discussion aimed at solving transaction conflicts and make better deals between trading entities in the commerce world. Negotiation is a major part of real life transactions. From major business deals to buying vegetables it acts as one of key the elements of cracking the deal. If implemented correctly in the rapidly growing E-commerce field it can increase the quality of the customer service. Customer satisfaction is the major concern for all the web based applications and chatbots helps them work this major concern as customers do not need wait for customer executives to solve their queries. Chatbots can solve most of the customer queries without the interference of customer executives. Thus, if a chatbot is able to implement negotiation then e-commerce websites will attract a lot of new consumers because of the features. Chat-bots are mainly used to provide conversation between both human and machine. Admin feed some knowledge to the machine so that machine can identify the sentences and taking a decision itself as response to answer a question . Negotiation is the process of exchange that provides the highest likelihood of satisfying the needs of both parties. Negotiation covers many aspects of our lives has led to extensive research in the area of automated negotiators . The E- Negotiator Chabot helps the user to solve query and provide negotiation mode is dis-satisfied with the price. Such system will help the users to freely interact with the software and upload their product related queries and budget and get the response related to the query. Just like retail and logistics companies use data to plot the most efficient route to deliver goods. We are providing the Negotiation mode in the proposed system so that user can use this particular mode if S/he is not happy with the price. When it comes to shopping negotiation is major component which impacts the deal. The process of satisfying the requirements of two or more parties in presence is called E – commerce negotiation which is a decision-making process of limited information and conflicting preferences.

Project Objectives

1.To provide negotiation to the user without the need of interacting with human instead by interacting with the chatbot.

2. To increase the quality of the customer service.

3. To solve query and provide negotiation mode is dis-satisfied with the price.

Project Implementation Method

Firstly, the system can load the data having questionnaires dataset related to the welcome messages, negotiation messages. While using the system user needs to ask a query. Then by using the tag word from the query system gives the response with the help of Natural Language Processing. If the user is not satisfied with the production budget then the user selects a product and starts a discussion on negotiation on the product with a chatbot. Following algorithms are used in the implementation:

Support Vector Machine Classification Algorithm: Support vector machine (SVM) proposed by vapnik and cortes have been successfully applied for gender classification problems by many researchers. An SVM classifier is a linear classifier where the separating hyper plane is chosen to minimize the expected classification error of the unseen test patterns. SVM is a strong classifier which can identify two classes. SVM classifies the test image to the class which has the maximum distance to the closest point in the training. SVM training algorithm built a model that predict whether the test image fall into this class or another. SVM require a huge amount of training data to select an affective decision boundary and computational cost is very high even if we restrict ourselves to single pose (frontal) detection. The SVM is a learning algorithm for classification. It tries to find the optimal separating hyper plane such that the expected classification error for unseen patterns is minimized. For linearly non-separable data the input is mapped to high-dimensional feature space where they can be separated by a hyper plane. This projection into high-dimensional feature space is efficiently performed by using kernels. More precisely, given a set of training samples and the corresponding decision values -1, 1 the SVM aims to find the best separating hyper plane given by the equation WTx+b that maximizes the distance between the two classes.

Benefits of the Project

We represent a E Negotiator chatbot for commercial websites which can help the users to get the product online according to their budget. Here user can directly interact with the system and get the response related to the query.

Implementing chatbots in rapidly growing e-commerce field can boost the customer service.

When it comes to shopping negotiation is major component which impacts the deal. We are providing the Negotiation mode in the proposed system so that user can use this particular mode if S/he is not happy with the price.

Technical Details of Final Deliverable

Whenever the user uses the system, firstly they need to mention their query. From the query the system can extract the tag word. And then according to the question tag system gives the response to user. The system can give the response to the user product queries. User has to type the product type and budget. The chat bot will search the most appropriate products as per user’s budget. Once the products are found matching to users search queries, then the list is returned. User selects a product and starts discussion on the product with chatbot. The agent begins by proposing a full offer, FA, as its anchor. FA is chosen by selecting the values for V with the highest value within the agents search cluster. It then takes offer from user and compares it with the minimum price. If it is greater than the minimum price then it accepts the deal else it uses the negotiation formula to offer a new reduced price to the user. If new reduced price is less than the minimum value then the chatbot offers the minimum value to the customer which he can accept or reject

Final Deliverable of the Project Software SystemCore Industry ITOther Industries Education Core Technology Artificial Intelligence(AI)Other Technologies Cloud InfrastructureSustainable Development Goals Quality EducationRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	79800
Stationary and thesis	Miscellaneous	2	5000	10000
smartphone for testing of the proejct	Equipment	1	27000	27000
LCD Monitor for testing resolution	Equipment	1	15000	15000
4TB Hard disk for huge storage	Equipment	1	18000	18000
Mic for recording purpose	Equipment	1	9800	9800