AI-Enabled Price Negotiation Chatbot Using Ensemble Classifier For E-Commerce Platform

Sunil Ghildiyal; Anurag Rai; Devesh Pratap Tiwari; Manvi Chopra; Aditi Joshi; Owais Farooq

doi:10.29284/vd6v2925

Authors

Sunil Ghildiyal School of Computing, DIT University Dehradun, India
Anurag Rai Department of Computer Science & Applications, Sharda School of Computing Science and Engineering, Sharda University, Greater Noida, India
Devesh Pratap Tiwari Department of Computer Science & Applications, Sharda School of Computing Science and Engineering, Sharda University, Greater Noida, India
Manvi Chopra School of Engineering and Computing, Dev Bhoomi Uttarakhand University, Dehradun, India
Aditi Joshi Department of Computer Science, Krishna Institute of Engineering & Technology (KIET), Ghaziabad, Delhi-NCR, Uttar Pradesh, India
Owais Farooq Department of Computer Science, Guru Nanak College Jhajra Dehradun, Uttarakhand, India

DOI:

https://doi.org/10.29284/vd6v2925

Keywords:

AI-Enabled Chatbot, Ensemble learning, Deep learning, Classifiers, E-commerce platform, Negotiation-based behavior.

Abstract

The high rate of growth of e-commerce site has heightened the necessity to implement smart and dynamic pricing systems that can adjust to varying customer tastes without losing the profitability of the sellers. The conventional fixed and rule-based approach to pricing is not capable of dynamically interacting with its customers and cannot respond to the negotiation-based buying behavior. This article aims to overcome this drawback by introducing a price negotiation chatbot based on AI that applies the principles of natural language processing and an ensemble classification model to facilitate price negotiation in real-time, in the form of a conversation, during online retail processes. The system suggested combines intent identification, sentiment analysis, and user behavioural modeling to derive valuable negotiation characteristics out of customer interaction. All these characteristics undergo processing by a pool of machine learning classifiers to identify the best negotiation behaviors, i.e. accept, counteroffer, or reject. Dynamically generated price recommendation strategy is then used to produce context sensitive counteroffers but within the business constraints which may be profit margins and inventory levels. Based on the experiments carried out on simulated e-commerce negotiation datasets, it can be proved that, compared to single classifiers, the suggested ensemble-based methodology is more accurate, has better F1-score, and negotiation success rate, as well as produces more deals. Findings also show better equilibrium between profit and customer satisfaction of the sellers as well as the shortest response latency and the system is appropriate to be used in real-time. The results present the strengths of the ensemble learning and conversational intelligence in automated pricing technology and present high potential of application to large scale e-commerce systems in the future.

References

[1] J. Gao, A. Promise Opute, and C. Jawad, “The influence of artificial intelligence chatbot problem solving on customers’ continued usage intention in e-commerce platforms: An expectation-confirmation model approach,” J. Bus. Res., vol. 155, pp. 115661, Nov. 2025.

[2] H. K. L. Chau, X. Cheng, and Y. Bao, “Human-AI interaction in e-commerce: The impact of AI on customer satisfaction and purchase intentions,” Comput. Hum. Behav., vol. 147, 2025.

[3] M. Madanchian et al., “The Impact of Artificial Intelligence Marketing on E-commerce Performance,” Systems, vol. 12, no. 10, p. 429, 2024.

[4] E. Dritsas and M. Trigka, “Machine Learning in E-Commerce: Trends, Applications, and Future Challenges,” IEEE Access, vol. 13, pp. 3572865, 2025.

[5] M. Nowak, “Dynamic Pricing Method in the E-Commerce Industry Using Machine Learning,” Appl. Sci., vol. 14, no. 24, p. 11668, 2024.

[6] N. Jahan, J. Ahamed, and D. Nandi, “Enhancing e-commerce sentiment analysis with advanced BERT techniques,” Int. J. Inf. Eng. Electron. Bus., vol. 17, no. 3, pp. 49–61, 2025.

[7] M. R. R. Rana et al., “BERT-BiGRU-Senti-GCN: An advanced NLP framework for analyzing customer sentiments in e-commerce,” Int. J. Comput. Intell. Syst., vol. 18, p. 21, 2025.

[8] Z. Ahmad et al., “INA: An integrative approach for enhancing negotiation strategies with reward-based dialogue system,” ACM Trans. AI, 2023 (preprint at arXiv).

[9] M. Vaccaro et al., “Advancing AI negotiations: New theory and evidence from a large-scale autonomous negotiations competition,” J. Artif. Intell. Res., 2025 (preprint at arXiv).

[10] X. Cheng et al., “Exploring consumers response to text-based chatbots in e-commerce: Task complexity and chatbot disclosure,” Electron. Markets, 2024 (preprint at arXiv).

[11] S. Gupta, R. Ranjan, and S. N. Singh, “Comprehensive framework for evaluating conversational AI chatbots,” AI Mag., 2025 (preprint at arXiv).

[12] Y. Kim et al., “Algorithmic collusion of pricing and advertising on e-commerce platforms,” Econ. Comput., 2025 (preprint at arXiv).

[13] L. Wang, Y. Li, and H. Zhang, “Dynamic pricing in e-commerce: A machine learning perspective,” Electron. Commer. Res. Appl., vol. 48, 2022.

[14] R. Singh and P. S. Kumar, “Sentiment-aware e-commerce recommendation using deep learning,” Inf. Process. Manage., vol. 58, no. 6, 2021.

[15] T. Nguyen and J. Simkin, “The dark side of AI in customer service: A critique and research agenda,” J. Bus. Res., vol. 147, pp. 558-573, 2023.

[16] J. Lee and S. Park, “Customer perception of e-commerce chatbots: Effects on satisfaction and loyalty,” J. Retail. Consum. Serv., vol. 67, 2022.

[17] M. Luo et al., “Explainable artificial intelligence for dynamic pricing decisions,” Decis. Support Syst., vol. 156, 2023.

[18] A. Pérez and F. García, “Reinforcement learning for pricing strategies in e-commerce,” Comput. Oper. Res., vol. 145, 2022.

[19] E. Papageorgiou, “AI-driven negotiation agents: Review and future directions,” Expert Syst. Appl., vol. 200, 2023.

[20] B. Zhang and T. Ke, “Sentiment analysis in e-commerce reviews: A deep learning survey,” IEEE Trans. Affective Comput., vol. 12, no. 2, 2023.

[21] M. Chen et al., “AI chatbot customer support performance and user satisfaction,” IEEE Access, vol. 10, pp. 76543–76555, 2022.

[22] L. Huang, “Personalized pricing and negotiation in e-commerce using hybrid ML models,” Inf. Sci., vol. 610, pp. 321–337, 2023.

[23] Y. Sun and M. Chen, “Multilingual sentiment and negotiation intent detection in e-commerce chatbots,” Multimodal Technol. Interact., vol. 7, no. 4, 2024.

[24] A. Verma and S. Roy, “Customer behavior prediction using ensemble classifiers for e-commerce personalization,” Soft Comput., vol. 28, pp. 14517–14533, 2024.

[25] L. Zhao and X. Wu, “Deep learning approaches to conversational agents in retail platforms,” Neural Comput. Appl., vol. 36, pp. 11251–11270, 2024.