Authors :
Sagar D. Patil; Dr. Manisha Bharati
Volume/Issue :
Volume 11 - 2026, Issue 5 - May
Google Scholar :
https://tinyurl.com/3h2zt23m
Scribd :
https://tinyurl.com/ye2x75hs
DOI :
https://doi.org/10.38124/ijisrt/26May1751
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
Fixed pricing in e-commerce platforms creates a significant gap compared to the interactive bargaining experience
customers enjoy in physical retail environments. This paper presents BargainBot, a deployed full-stack AI chatbot that
enables real-time, free-form price negotiation on e-commerce platforms. The proposed system integrates three core
components:
A PyTorch Recurrent Neural Network (RNN) trained on a custom multilingual intent dataset spanning English, Hindi,
and Marathi, achieving approximately 91% classification accuracy across 15 negotiation intent classes.
A rule-based negotiation engine that enforces per-product seller margin constraints while generating contextually
appropriate counter-offers.
A sentiment-aware response layer that detects buyer tone and adjusts negotiation strategy accordingly.
Unlike prior work that relies on fixed command keywords or scripted menus, BargainBot accepts fully free-form
natural-language input, disambiguates discount-amount offers from target-price offers, and maintains offer state across
multiple conversation turns. The system is implemented as a decoupled React.js frontend communicating with a Django
REST backend, supporting 37 products across six categories. Experimental evaluation demonstrates a negotiation success
rate of 84%, intent classification accuracy of ~91%, and 100% seller margin protection across all tested scenarios.
Keywords :
Price Negotiation, E-Commerce Chatbot, Recurrent Neural Network, Intent Classification, Natural Language Processing, Multi-Turn Dialogue, Rule-Based Reasoning, Sentiment Analysis, Dynamic Pricing.
References :
- A. Bhamre, S. Kulkarni, S. Kulkarni, S. Khandelwal, and A. Jain, "Price Negotiator Bot: Bargain Buddy," Int. J. Innovative Research in Sci., Eng. & Technol., vol. 12, no. 3, pp. 2326–2329, Mar. 2023.
- D. H. Bindu, V. Manasa, P. Karthik, R. Shalini, and T. D. Rao, "Price Negotiating Chatbot on E-Commerce Website Using NPL," Int. J. Advanced Research in Sci., Commun. & Technol., vol. 3, no. 3, pp. 475–477, Apr. 2023.
- S. Surekha et al., "Price Negotiating Chatbot with Text and Voice on E-Commerce Website," Int. J. Novel Research and Development, vol. 9, no. 3, pp. 103–110, Mar. 2024.
- B. U. Sri et al., "Price Negotiation Chatbots on E-Commerce Website Using Machine Learning," Int. J. Creative Research Thoughts, vol. 12, no. 5, pp. D481–D486, May 2024.
- Y. Challagundla et al., "Integrating Intellectual Consciousness AI Based on Ensemble Machine Learning for Price Negotiation in E-Commerce," EAI Endorsed Trans. Internet of Things, vol. 10, 2024.
- M. Rana, P. Ghonge, and S. Sall, "Smart Price Negotiator: An Integrated NLP and Reinforcement Learning-Based Chatbot," Int. J. Food and Nutritional Sciences, vol. 10, no. 6, pp. 564–573, 2021.
- S. Pappala et al., "Smart Bargain Bot: A Text and Voice-Based Price Negotiation System for E-Commerce Platforms," Int. J. on Science and Technology, vol. 16, no. 2, pp. 1–11, Apr.–Jun. 2025.
- B. S. Metre, V. S. Gulhane, and H. N. Datir, "Price Negotiation Chatbot Using AI-Based Ensemble Machine Learning Techniques," Int. J. Innovative Research in Technology, vol. 11, no. 11, pp. 1682–1687, Apr. 2025.
- B. M. Prasad, P. Valluru, and A. Rani, "AI-Driven Negotiation Chatbot for Dynamic Pricing in E-Commerce Platforms," Int. J. Novel Research and Development, vol. 10, no. 5, pp. 850–854, May 2025.
- S. D. Patil, R. Dharmadhikari, and M. Bharti, "BargainBot: AI-Driven Price Negotiation for E-Commerce – A Review," Int. J. Innovative Research in Technology, vol. 12, no. 10, pp. 2082–2083, Mar. 2026.
- T. Liu and Z. Zheng, "Negotiation Assistant Bot of Pricing Prediction Based on Machine Learning," Int. J. Intelligence Science, vol. 10, no. 2, pp. 9–21, Apr. 2020.
- J. R. Oliver, "A Machine-Learning Approach to Automated Negotiation and Prospects for Electronic Commerce," J. Management Information Systems, vol. 13, no. 3, pp. 83–112, 1996.
- M. Lewis et al., "Deal or No Deal? End-to-End Learning for Negotiation Dialogues," in Proc. EMNLP, Copenhagen, Denmark, 2017, pp. 2443–2453.
- D. Silver et al., "A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play," Science, vol. 362, no. 6419, pp. 1140–1144, 2018.
Fixed pricing in e-commerce platforms creates a significant gap compared to the interactive bargaining experience
customers enjoy in physical retail environments. This paper presents BargainBot, a deployed full-stack AI chatbot that
enables real-time, free-form price negotiation on e-commerce platforms. The proposed system integrates three core
components:
A PyTorch Recurrent Neural Network (RNN) trained on a custom multilingual intent dataset spanning English, Hindi,
and Marathi, achieving approximately 91% classification accuracy across 15 negotiation intent classes.
A rule-based negotiation engine that enforces per-product seller margin constraints while generating contextually
appropriate counter-offers.
A sentiment-aware response layer that detects buyer tone and adjusts negotiation strategy accordingly.
Unlike prior work that relies on fixed command keywords or scripted menus, BargainBot accepts fully free-form
natural-language input, disambiguates discount-amount offers from target-price offers, and maintains offer state across
multiple conversation turns. The system is implemented as a decoupled React.js frontend communicating with a Django
REST backend, supporting 37 products across six categories. Experimental evaluation demonstrates a negotiation success
rate of 84%, intent classification accuracy of ~91%, and 100% seller margin protection across all tested scenarios.
Keywords :
Price Negotiation, E-Commerce Chatbot, Recurrent Neural Network, Intent Classification, Natural Language Processing, Multi-Turn Dialogue, Rule-Based Reasoning, Sentiment Analysis, Dynamic Pricing.