DBOT: Artificial Intelligence for Systematic Long-Term Investing
Vasant Dhar, João Sedoc
TL;DR
DBOT proposes a digital analytic twin that imitates Damodaran’s valuation process for long-horizon investing, using a modular, multi-agent LLM architecture to produce back-testable valuations $v$ via the Damodaran framework $f^{fcf}$ and related inputs. It integrates specialized agents (valuation, news, consensus, comparables, sensitivity, plotting, reporting) under a supervisor to generate transparent narratives and visuals, enabling systematic, auditable long-term analysis. The paper demonstrates DBOT on BYD, obtaining a stable $v$ around $420 per share within a $417$–$468$ range and detailing drivers, sensitivities, and market-context considerations, while critically examining limitations such as framing-question generation and tacit knowledge transfer. Implications point to broader industry impact, including productivity gains for analysts, regulatory considerations for autonomous AI investment tools, and the need for continued enhancement of domain-specific LLMs and backtesting frameworks.
Abstract
Long-term investing was previously seen as requiring human judgment. With the advent of generative artificial intelligence (AI) systems, automated systematic long-term investing is now feasible. In this paper, we present DBOT, a system whose goal is to reason about valuation like Aswath Damodaran, who is a unique expert in the investment arena in terms of having published thousands of valuations on companies in addition to his numerous writings on the topic, which provide ready training data for an AI system. DBOT can value any publicly traded company. DBOT can also be back-tested, making its behavior and performance amenable to scientific inquiry. We compare DBOT to its analytic parent, Damodaran, and highlight the research challenges involved in raising its current capability to that of Damodaran's. Finally, we examine the implications of DBOT-like AI agents for the financial industry, especially how they will impact the role of human analysts in valuation.