Dhagash Mehta

In this article, the authors introduce a public market equivalent framework to estimate default risk for private firms when financial statement fundamentals are unavailable or stale. The approach learns a supervised similarity metric from publicly traded corporate bond (from both public and private issuers) characteristics and risk measures using a random forest model and then uses random forest geometry- and accuracy-preserving (RF-GAP) proximities to identify a small, sector-consistent set of comparable public issuers for each private issuer. Comparable issuers’ ratings are aggregated into a similarity-weighted implied rating for the private issuer, which is subsequently mapped to a rating-implied probability of default using transition and default statistics. The framework is designed to balance predictive accuracy with interpretability by providing a transparent, peer-based explanation of each private issuer’s inferred credit quality.

As digital ecosystems expand in scale and complexity, malicious actors continually evolve their tactics, necessitating highly sophisticated defense mechanisms. The 1st Workshop on AI for Fraud and Abuse, held in conjunction with KDD 2026, bridges industry and academia to address these challenges. This workshop highlights the latest advancements in artificial intelligence tailored for trust and safety, with a specific focus on leveraging Generative AI, addressing real-world application challenges, navigating ethical and regulatory landscapes, and advancing open science through benchmarking. Through a combination of expert keynotes and peer-reviewed technical presentations, the workshop aims to foster collaboration and accelerate the development of robust, scalable fraud detection systems.

Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and adaptive agents. Agentic memory refers to the memory that provides an LLM with agent-like persistence: the ability to retain and act upon information across conversations, similar to how a human would. We present Memoria, a modular memory framework that augments LLM-based conversational systems with persistent, interpretable, and context-rich memory. Memoria integrates two complementary components: dynamic session-level summarization and a weighted knowledge graph (KG)-based user modelling engine that incrementally captures user traits, preferences, and behavioral patterns as structured entities and relationships. This hybrid architecture enables both short-term dialogue coherence and long-term personalization while operating within the token constraints of modern LLMs. We demonstrate how Memoria enables scalable, personalized conversational artificial intelligence (AI) by bridging the gap between stateless LLM interfaces and agentic memory systems, offering a practical solution for industry applications requiring adaptive and evolving user experiences.

Clustering and similarity learning are increasingly indispensable for structuring heterogeneous financial data and supporting real-world decision-making. Traditional heuristics such as industry codes, static style boxes, or return correlations offer only coarse and rigid notions of peer groups. Recent advances in metric learning, graph methods, and large language models now make it possible to build adaptive neighborhoods of securities, funds, companies, and investors that align more closely with actual risk, liquidity, and thematic exposures. This tutorial synthesizes these methodological developments and demonstrates their use across major asset classes. Case studies show how supervised proximities improve bond substitution, how fund similarity systems reconcile category reproducibility with outlier detection, how multimodal pipelines refine company comparables for valuation and strategy, and how investor clustering enhances personalization and “know your client” (KYC) analytics. We emphasize modeling choices that make clustering and similarity auditable and robust under regime shifts. We also outline their evaluation protocols such as neighborhood stability, substitution fidelity, and segment utility, and so on, which align with investment, compliance, and fiduciary objectives. Overall, the central message for practitioners is pragmatic: Similarity systems have moved beyond experimental prototypes and now stand as deployable techniques within real investment workflows.