Application of Startup Success Prediction Models and Business Document Extraction Using Large Language Models to Enhance Due Diligence Efficiency

EasyChair Preprint 14731

Abstract

Startups face extreme uncertainty and high failure rates, posing challenges for investors in identifying promising ventures. This research, based on a case study and interviews at a prominent Indonesian corporate venture capital firm, explores the due diligence process, typically taking 4-6 weeks depending on data completeness. Using Large Language Model (LLM) and Machine Learning (ML) technologies developed with the Team Data Science Process (TDSP) methodology, the research aims to enhance due diligence efficiency. Key development steps include data integration, ML model creation for startup success classification, and the integration of OpenAI's GPT-4 and Google Search APIs for comprehensive business analysis. The system's dashboard offers features such as pitch deck, financial, market trends, competitor, and founding team analyses, along with startup success prediction using the XGBoost model. This model, deployed via Flask, demonstrated consistent results through cross-validation. Customer acceptance testing, conducted with eight experienced startup investors, yielded a high satisfaction rate of 4.50 out of 5.00, indicating strong approval of the system's effectiveness.

Keyphrases: Due Diligence Process, GPT-4, Google Search API, Large Language Model (LLM), Venture Capital, accuracy of analysis results, analysis results, ease of use accuracy and relevance, efficiency of due diligence, machine learning

@booklet{EasyChair:14731,
  author    = {Vito Christian Samudra and Dicky Prima Satya},
  title     = {Application of Startup Success Prediction Models and Business Document Extraction Using Large Language Models to Enhance Due Diligence Efficiency},
  howpublished = {EasyChair Preprint 14731},
  year      = {EasyChair, 2024}}