{"paper_id":"2510.15942","title":"Intrinsic Geometry of the Stock Market from Graph Ricci Flow","authors":["Bhargavi Srinivasan"],"paper_date":"2025-10-09","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.15942v1","page_url":"https://thequant.space/flowcharts/intrinsic-geometry-of-the-stock-market-from-graph-ricci-flow/","scores":{"empirical_rigor":6,"math_complexity":9.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an algorithm that uses discrete Ollivier‑Ricci curvature and Ricci flow with surgery to detect hidden hierarchies, community behavior, and clustering in the fully‑connected NASDAQ‑100 correlation graph without assumptions on the number of clusters.","quote":"Our main result is the development of a technique to perform surgery on the neckpinch singularities that form during the Ricci flow of the empirical graph, using the behavior and the lower bound of curvature of the fully connected graph as a starting point. We construct an algorithm that uses the curvature generated by intrinsic geometric flow of the graph to detect hidden hierarchies, community behavior, and","summary":"We use the discrete Ollivier-Ricci graph curvature with Ricci flow to examine the intrinsic geometry of financial markets through the empirical correlation graph of the NASDAQ 100 index. Our main result is the development of a technique to perform surgery on the neckpinch singularities that form…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A lazy random walk probability measure with idleness parameter α = 1/2 is used for the curvature calculations.","type":"model","stated":"explicit","quote":"As explained in the appendix, we use a lazy random walk probability measure, with idleness parameter α = 1/2. Therefore, we drop the α index, with the understanding that α = 1/2 in this work.","support":"full"},{"assumption":"The empirical correlation graph is treated as a fully connected network with initially positive curvature.","type":"data","stated":"explicit","quote":"It is interesting to note that the fully connected graph which satisfies strict positivity of the curvature before the Ricci flow, still obeys the lower bound condition, even with unequal edge weights.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"NASDAQ‑100 stock price data","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2020-01-01 to 2024-11-20","universe":"NASDAQ‑100 constituents","quote":"We recovered the values of stock prices from Yahoo! Finance[32] using the components of the NASDAQ-100 Index from [33].","support":"partial","known_id":"yahoo-finance"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"After 20 iterations of Ricci flow with surgery the graph splits into two communities with very short edge weights and positive curvature, separated by long flat links of curvature zero and edge weights around 3.","kind":"theoretical","quote":"We find after 20 iterations that the graph splits into two communities, with very short edge weights and positive curvature. These two communities are separated by long, flat links with curvature zero and edge weights around 3.","support":"full"},{"finding":"The curvature lower bound (≈ −1.96) provides a reliable index for community detection, as the edge length behavior differs for positive and negative curvature cases.","kind":"theoretical","quote":"For the NASDAQ-100 graph this gives κij,min ≈−1.96. Therefore identifying the lower bound of the curvature is a more reliable index for community detection.","support":"full"},{"finding":"The algorithm can cluster the NASDAQ‑100 into two groups of 66 and 35 stocks, with the larger group further subdividing into a basket of 16 semiconductor stocks after a second level of Ricci flow and surgery.","kind":"theoretical","quote":"After the first level of Ricci flow, followed by surgery us-ing the method described above, the cluster splits into two communities of 66 and 35 stocks. The second level of Ricci flow leads to a basket of 16 semi-conductor stocks.","support":"partial"},{"finding":"The curvature‑based approach offers an attractive alternative to minimum spanning tree methods for studying geometric properties of the stock market.","kind":"theoretical","quote":"Our curva-ture based approach provides an attractive alternative to MST to study the geometric properties of the stock market.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":11,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":1,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[{"paper":{"paper_id":"2605.11645","title":"GeomHerd: A Forward-looking Herding Quantification via Ricci Flow Geometry on Agent Interactive Simulations","paper_date":"2026-05-12","authors":["Lake Yang","Junwei Su","Jingfeng Zeng","Wenhao Lu","Xingzhi Qian","Weitong Zhang"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/geomherd-a-forward-looking-herding-quantification-via-ricci-flow-geometry-on/"},"how":"used_as_baseline","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:47:05Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}