On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “conglomerates”

Multi-Industry Simplex 2.0 : Temporally-Evolving Probabilistic Industry Classificationq-fin.PM

Improves industry classification for diversified companies.

problem Traditional industry classification struggles with multi-sector conglomerates.

method Bayesian Non-Parametrics, Markov Updating, and hierarchical modeling.

result MIS-2 provides a measurable improvement over GICS in predicting future correlations.

industry classification portfolio management Bayesian non-parametrics Markov updating hierarchical modeling

2024-07-23abs ↗pdf ↗

Network analysis of Japanese global business using quasi-exhaustive micro-data for Japanese overseas subsidiariesq-fin.GN

Study uses network analysis to examine Japanese overseas business networks.

problem Challenges the weak evidence supporting the existence of Japanese conglomerates (HK).

method Large dataset of 20,000 Japanese overseas subsidiaries analyzed using network techniques.

result Rejects Miwa-Ramseyer hypothesis (MRH) for global and regional datasets.

network analysis Japanese business overseas subsidiaries conglomerates Miwa-Ramseyer hypothesis

2017-07-18abs ↗pdf ↗

Polyspectral Mean based Time Series Clustering of Indian Stock Marketq-fin.ST

Study clusters Indian stocks using polyspectral means for nuanced market insights.

problem Analyzing temporal patterns and financial relationships in Indian stock market.

method k-means clustering algorithm applied to polyspectral means of stock data.

result Identified five distinctive clusters of stocks with varying ownership structures.

Indian stock market k-means clustering polyspectral means time series analysis financial relationships

2025-04-09abs ↗pdf ↗

Multi-Industry Simplex : A Probabilistic Extension of GICSq-fin.PM

Develops MIS, a probabilistic model for multi-industry classification.

problem GICS's limitation of assigning each firm to exactly one industry, especially for diversified firms.

method Topic modeling to probabilistically assign firms to multiple industries based on business descriptions.

result Demonstrates MIS's ability to flexibly assign firms to multiple industries with relevance probabilities.

industry classification probabilistic modeling topic modeling asset management thematic portfolios

2023-10-06abs ↗pdf ↗

From Predictive to Prescriptive Analyticsstat.ML

In this paper, we combine ideas from machine learning (ML) and operations research and management science (OR/MS) in developing a framework, along with specific methods, for using data to prescribe optimal decisions in OR/MS problems. In a departure from other work on data-driven optimization and reflecting our practic…

2014-02-22abs ↗pdf ↗