AI in Financial Services: Automated Company Valuation
summary
A web tool running on GCP automates valuation for six Zagreb Prime Market firms by extracting Excel and PDF financial statements into Postgres then converting historical tables into LLM-readable text to produce DCF comparable and asset based valuations and visual KPI reports The pipeline uses GCP Cloud Run & Functions for ingestion and preprocessing Postgres + Pinecone vector DB for structured and semantic storage and OpenAI LLMs + Vertex AI agent for summaries Q&A and ESG CEO extraction Costs are small at current scale and a multi agent setup is under test
AI-written summary · about
chapters (18)
- 0:00AI in company valuation
- 1:07Traditional valuation methods
- 3:58Manual valuation challenges
- 6:26Automated AI solution project
- 8:18Phases of automated evaluation
- 10:08Solution architecture
- 11:14AI extraction of financial metrics
- 12:19LLMs summarizing performance
- 13:24PDF financial report processing
- 14:08CEO insights from reports
- 15:13Gathering ESG information from reports
- 16:38Interactive AI insights
- 18:44AI solution benefits
- 19:47Future multi-agent directions
- 20:52Q&A: Plug-and-play costs
- 23:46Q&A: Startup acquisitions
- 25:35Q&A: Solip’s background
- 27:03Q&A: Cloud and agents
related talks
20mGetting business value from AI: Everyday AI, extraordinary people
59mAI in Finance: Scope and Examples- 59mAI in Finance: Scope and Examples
27mAI as a Service Scaling AI with Ease and Innovation
26mAI Agents as Financial Co-Pilots | AI-Driven Strategy & Decision Making
47mAI Pitch: Beyond the Hype
22mAI Driven Financial Workflows: Lessons from Scaling for SMEs
59mContinuous Intelligence: Keeping your AI Application in Production