IRO Journals
Journal of Information Technology and Digital World

StartVerse: An AI-Driven Chatbot for Startup Intelligence and Market Analysis

Open Access
Published: 13 June, 2026
Pages: 167-177
  • Preethi G. , Preethi G.
    Assistant Professor, Department of Information Technology, Velammal Engineering College, Chennai, India
    Assistant Professor, Department of Information Technology, Velammal Engineering College, Chennai, India
  • Kavyaa T. , Kavyaa T.
    Student, Department of Information Technology, Velammal Engineering College, Chennai, India
    Student, Department of Information Technology, Velammal Engineering College, Chennai, India
  • Hemalatha B. Hemalatha B.
    Student, Department of Information Technology, Velammal Engineering College, Chennai, India
    Student, Department of Information Technology, Velammal Engineering College, Chennai, India
view PDF
view PDF

How to Cite

G., Preethi, Kavyaa T., and Hemalatha B. 2026. “StartVerse: An AI-Driven Chatbot for Startup Intelligence and Market Analysis”. Journal of Information Technology and Digital World 8 (3): 167-77. https://doi.org/10.36548/jitdw.2026.3.003.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Startup Intelligence
Artificial Intelligence
Conversational AI
Retrieval-Augmented Generation
Predictive Analytics
Business Intelligence
Market Analysis

Abstract

Start-ups function in very dynamic settings where the availability of up-to-date market intelligence is key for informed decision making. Current startups analysis methods depend on unreliable sources of data, manual analysis, and ineffective business intelligence, thus, hindering their ability to generate useful insights in a dynamic market environment. The current study proposes the development of an AI-Driven Startup Intelligence Chatbot called "StartVerse." The chatbot utilizes real-time data gathering, Natural Language Processing, Retrieval Augmented Generation, predictive analytics, and interactive dashboards to provide reliable and relevant business insights. Specifically, the proposed system integrates Large Language Models with ARIMA and LSTM-based forecast models to help startups validate ideas, perform competitor analysis, monitor industry trends, and make strategic decisions. The experimental analysis showed that the system is capable of providing accurate and contextual insights with response time lower than two seconds and superior usability compared to the current methods of startup analysis.

References

  1. Davenport, Thomas H. "Competing on Analytics." Harvard business review 2006, vol. 84, no. 1: 98.
  2. Chen, Hsinchun, Roger HL Chiang, and Veda C. Storey. "Business Intelligence and Analytics: From Big Data to Big Impact." MIS quarterly 2012, vol. 36, no. 4: 1165-1188.
  3. Provost, Foster, and Tom Fawcett. "Data Science for Business.", O’Reilly Media, 2013. Vol. 8, no. 6: 366.
  4. Goodfellow, Ian, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. Deep Learning., Cambridge: MIT press, 2016, vol. 1, no. 2.
  5. Hochreiter, Sepp, and Jürgen Schmidhuber. "Long Short-Term Memory." Neural computation 1997, vol. 9, no. 8: 1735-1780.
  6. Box, George EP, Gwilym M. Jenkins, Gregory C. Reinsel, and Greta M. Ljung. Time Series Analysis: Forecasting and Control. John Wiley & Sons, 2015.
  7. Daniel Jurafsky and James H. Martin. “Speech and Language Processing: An Introduction to Natural Language Processing.”, Computational Linguistics, and Speech Recognition with Language Models 2026. https://web.stanford.edu/~jurafsky/slp3.
  8. Russell, S., & Norvig, P. Artificial Intelligence: A Modern Approach, 4th Edition, Pearson Education 2021.
  9. Ashish, Vaswani. "Attention is All You Need." 31st Conference on Neural Information Processing Systems 2017, 30: I.
  10. Kotu, Vijay, and Bala Deshpande. Predictive Analytics and Data Mining: Concepts and Practice with Rapidminer. Morgan Kaufmann, 2014.