Summary
Analysts studying stock markets often answer the same questions but use different spreadsheets that are hard to check or trust. The authors created OntoKG-EQ, a system that organizes data and calculations into a knowledge graph, linking every answer to its original evidence and steps. This makes the results easy to inspect, consistent, and reproducible across different markets without changing the setup. Their tests showed that people trusted the answers more when the evidence was clearly presented, and the system also helps measure how well language AI models understand the evidence. The code and data are freely available for others to use.
Knowledge graphOntologyProvenanceCompetency questionsMarket analysisReproducibilityData validationGraph queryExplainabilityLanguage models
Authors
Furqan Nasir, Muhammad Atif Saeed, Muhammad Ehsan, Sher Jeel Ahmad, Abdul Moiz Altaf
Abstract
Analysts in emerging equity markets keep answering the same questions. Did fundamentals match the market's response? How does the local currency co-move with returns? Which firms outperform sector and benchmark, and which disclosures coincide with abnormal trading? These answers come from ad-hoc spreadsheets that are hard to reproduce, audit, or trust. We present OntoKG-EQ, a knowledge-based system that makes such queries reproducible, evidence-linked, temporally explicit, valid, and inspectable. It couples a bounded, competency-question-governed core ontology with a provenance-aware knowledge graph in which every class, property, shape, and metric is justified by one of five frozen questions. The system materialises market data into the graph, computes the metrics, validates its structure against declarative shape constraints, answers each competency question with a graph query, derives typed findings, and generates an explanation tracing each result to its observations, evidence, sources, and provenance. We evaluate on curated datasets from three emerging markets (Pakistan, Malaysia, Indonesia). Once each market's data is mapped into the common schema, the ontology, shapes, queries, and rules are reused unchanged. A relational-database baseline shows the graph changes no analytics. Its value is governance, provenance, and self-explaining structure. Because answers are rendered deterministically from the validated graph, their consistency with it is guaranteed by construction. Used as a reference, the system measures how consistently eight open language models transcribe the same evidence (provenance coverage 0.00 to 1.00). A study with a 17-participant convenience panel finds the evidence bundle significantly increased perceived trust and completeness. Code and data are openly released.