You can discover new insights with AI

An investment fund struggled to analyze financial data from its private company holdings and potential investments. Unlike public companies, private firms do not follow any uniform standard, resulting in varied terminology for key metrics and various formats, such as PDFs and Excel spreadsheets. As a result, much of this information is unstructured and difficult to analyze, reflecting the 80-90% of the world’s data that remains untapped.¹

Current automation tools and new start-ups did not fully meet the fund’s needs, forcing analysts to manually review documents to extract key performance data. This process is not only time-consuming, but also prone to errors, risking the fund’s ability to uncover valuable insights that could enhance decision-making and overall performance.

KPMG developed a generative AI tool that quickly and accurately analyzes unstructured data from private companies, including financial information. The tool mimics the analytical reasoning of a Chartered Professional Accountant (CPA), achieving 98% accuracy in interpreting financial statements. As a result, it extracts more data and delivers richer analyses in significantly less time.

KPMG automation consultants worked closely with CPAs to outline the logical processes accountants use to identify key financial metrics. The AI model uses thousands of specialized prompts to incorporate contextual information, such as industry-specific guidelines and financial details, enabling accurate and precise analysis.

For example, rather than searching for specific terms like “total debt,” which may not appear in every statement, the team created an AI-based persona that mirrors CPA-level thinking. This allows the program to intelligently identify relevant metrics, such as long-term and short-term debt, while excluding liabilities that do not incur interest. The model can also answer specific questions about the company, including key financial ratios, or even exposure to cryptocurrencies.

The tool features advanced multi-modal capabilities, enabling it to read files in any format while maintaining the document’s structure and logic. To mitigate risk, the team used anonymized financial documents in a secure environment.

KPMG integrated the AI tool into the client’s workflow. On a monthly basis, it ingests the financial statements of portfolio companies and outputs the necessary fields. Data analysts receive prompts to confirm accuracy before forwarding the information to investment analysts, all within a user-friendly interface for seamless validation.

KPMG’s financial extraction tool significantly outperformed human analysis, achieving 98% accuracy and a perfect Net Promoter Score (NPS) of 100 from initial users. The client is now developing a roadmap for new features to analyze contracts, investment risks, and ESG reports.

The key outcome for the client is the ability to extract more data quickly, enabling richer analysis in a fraction of the time. This capability is crucial for an investment fund that needs to operate at “deal-speed.”

Additionally, the AI tool allows the client to handle a larger volume of data without increasing its workforce. As confidence in the tool’s accuracy grows, the potential for fully automated processing of financial statements could save the fund up to 15 full-time equivalent (FTE) positions. Interestingly, the client has found that bypassing human validation could actually improve the tool's accuracy, as human involvement has occasionally introduced errors.

In addition to operational efficiency, the AI solution has unlocked valuable financial data and insights that were previously out of reach . By combining professional expertise with advanced AI, the client now generates insights that lead to smarter, more strategic decisions—positioning the fund for growth and higher returns.

Discover how we’re making a difference for Canadian organizations