arXiv subjects

Teruo Nakatsuma

Publications and source records attributed to Teruo Nakatsuma.

8 recordsLinked to original sources

arXiv2026

tse_tick: A Python Library for Parsing and Querying Nikkei NEEDS Tick Data from the Tokyo Stock Exchange

Tick-level trade-and-quote data for the Tokyo Stock Exchange is distributed through the Nikkei NEEDS service as thousands of zipped CSV archives spanning four data types with era-dependent schemas and Japanese-language layouts. We present tse_tick, an open-source Python library that converts these raw archives into clean, typed Polars DataFrames and a Hive-partitioned Parquet store queryable through DuckDB. The library offers two access paths sharing one parse-and-clean core: a one-shot reader that returns a ticker- and time-filtered DataFrame directly from raw ZIP files, and a two-stage ingest-then-query pipeline with resume-safe, memory-aware parallel ingestion, part-pruning, and a materialized intraday time key for row-group pruning. The engineering, more than the parsing, is what the library contributes: ingestion runs in per-date atomic units whose completion is recorded by coverage markers rather than inferred from file existence, writes stream in bounded morsels so that peak memory is independent of trading-day size (24.5 GB to 2.4 GB on the worst measured day), a RAM-aware process pool sizes itself to available memory, and part-pruning opens only the archive parts a ticker can occupy. Full English and Japanese column definitions ship for all four types, and a translation layer maps yfinance, Polygon, and ccxt names onto their tse_tick equivalents. In benchmarks on a commodity 16-thread workstation, parsing a representative 4.8-million-row archive part, one of a trading day's nine parts, is 59.8x faster than the original pandas prototype (34.3x against an engine-matched pandas baseline), and a single-ticker time-window query from the store completes roughly 410x faster than a pandas scan of the equivalent CSV. tse_tick is available on PyPI (pip install tse-tick) under the MIT license.

q-fin.TR↗

arXiv2026

Calibrated Horizon-Weighted Local Projection Designs for Markov Switchbacks

We study temporal assignment design for Markov switchback experiments when the reported object is a dynamic local-projection target. We develop a calibrated selector that chooses the feasible persistence minimizing the covariance, HAC, residual-bootstrap, or realized-schedule risk of the estimator and reporting object specified before the experiment. A balanced homoskedastic Markov benchmark yields a closed form because the lagged-assignment information matrix is AR(1)-Toeplitz with a tridiagonal inverse. The benchmark maps local-projection reporting weights into persistence recommendations within a prespecified first-order Markov class. Field recommendations replace the benchmark covariance with residualized, serially dependent, pilot-calibrated, or randomization-based risk. A semi-synthetic Low Carbon London evaluation uses observed half-hourly baseline dynamics and known injected responses to assess design risk. It evaluates the covariance calculations under realistic load autocovariance and identifies when calibrated covariance selection should replace the homoskedastic Markov formula. Near-boundary designs use randomization-first inference when many-spell normal approximations are unsupported.

stat.ME↗

arXiv2025

Convergence Rate of Efficient MCMC with Ancillarity-Sufficiency Interweaving Strategy for Panel Data Models

Improving Markov chain Monte Carlo algorithm efficiency is essential for enhancing computational speed and inferential accuracy in Bayesian analysis. These improvements can be effectively achieved using the ancillarity-sufficiency interweaving strategy (ASIS), an effective means of achieving such gains. Herein, we provide the first rigorous theoretical justification for applying ASIS in Bayesian hierarchical panel data models. Asymptotic analysis demonstrated that when the product of prior variance of unobserved heterogeneity and cross-sectional sample size N is sufficiently large, the latent individual effects can be sampled almost independently of their global mean. This near-independence accounts for ASIS's rapid mixing behavior and highlights its suitability for modern "tall" panel datasets. We derived simple inequalities to predict which conventional data augmentation scheme-sufficient augmentation (SA) or ancillary augmentation (AA)-yields faster convergence. By interweaving SA and AA, ASIS achieves optimal geometric rate of convergence and renders the Markov chain for the global mean parameter asymptotically independent and identically distributed. Monte Carlo experiment confirm that this theoretical efficiency ordering holds even for small panels (e.g., N=10). These findings confirm the empirical success of ASIS application across finance, marketing, and sports, laying the groundwork for its extension to models with more complex covariate structures and nonGaussian specifications.

stat.ME↗

arXiv2024

Do GPT Language Models Suffer From Split Personality Disorder? The Advent Of Substrate-Free Psychometrics

Previous research on emergence in large language models shows these display apparent human-like abilities and psychological latent traits. However, results are partly contradicting in expression and magnitude of these latent traits, yet agree on the worrisome tendencies to score high on the Dark Triad of narcissism, psychopathy, and Machiavellianism, which, together with a track record of derailments, demands more rigorous research on safety of these models. We provided a state of the art language model with the same personality questionnaire in nine languages, and performed Bayesian analysis of Gaussian Mixture Model, finding evidence for a deeper-rooted issue. Our results suggest both interlingual and intralingual instabilities, which indicate that current language models do not develop a consistent core personality. This can lead to unsafe behaviour of artificial intelligence systems that are based on these foundation models, and are increasingly integrated in human life. We subsequently discuss the shortcomings of modern psychometrics, abstract it, and provide a framework for its species-neutral, substrate-free formulation.

cs.CL↗

arXiv2022

A positive-definiteness-assured block Gibbs sampler for Bayesian graphical models with shrinkage priors

Although the block Gibbs sampler for the Bayesian graphical LASSO proposed by Wang (2012) has been widely applied and extended to various shrinkage priors in recent years, it has a less noticeable but possibly severe disadvantage that the positive definiteness of a precision matrix in the Gaussian graphical model is not guaranteed in each cycle of the Gibbs sampler. Specifically, if the dimension of the precision matrix exceeds the sample size, the positive definiteness of the precision matrix will be barely satisfied and the Gibbs sampler will almost surely fail. In this paper, we propose modifying the original block Gibbs sampler so that the precision matrix never fails to be positive definite by sampling it exactly from the domain of the positive definiteness. As we have shown in the Monte Carlo experiments, this modification not only stabilizes the sampling procedure but also significantly improves the performance of the parameter estimation and graphical structure learning. We also apply our proposed algorithm to a graphical model of the monthly return data in which the number of stocks exceeds the sample period, demonstrating its stability and scalability.

stat.CO↗

arXiv2021

Identification in Bayesian Estimation of the Skewness Matrix in a Multivariate Skew-Elliptical Distribution

Harvey et al. (2010) extended the Bayesian estimation method by Sahu et al. (2003) to a multivariate skew-elliptical distribution with a general skewness matrix, and applied it to Bayesian portfolio optimization with higher moments. Although their method is epochal in the sense that it can handle the skewness dependency among asset returns and incorporate higher moments into portfolio optimization, it cannot identify all elements in the skewness matrix due to label switching in the Gibbs sampler. To deal with this identification issue, we propose to modify their sampling algorithm by imposing a positive lower-triangular constraint on the skewness matrix of the multivariate skew- elliptical distribution and improved interpretability. Furthermore, we propose a Bayesian sparse estimation of the skewness matrix with the horseshoe prior to further improve the accuracy. In the simulation study, we demonstrate that the proposed method with the identification constraint can successfully estimate the true structure of the skewness dependency while the existing method suffers from the identification issue.

stat.ME↗

arXiv2017

Volatility Forecasts Using Nonlinear Leverage Effects

The leverage effect-- the correlation between an asset's return and its volatility-- has played a key role in forecasting and understanding volatility and risk. While it is a long standing consensus that leverage effects exist and improve forecasts, empirical evidence paradoxically do not show that most individual stocks exhibit this phenomena, mischaracterizing risk and therefore leading to poor predictive performance. We examine this paradox, with the goal to improve density forecasts, by relaxing the assumption of linearity in the leverage effect. Nonlinear generalizations of the leverage effect are proposed within the Bayesian stochastic volatility framework in order to capture flexible leverage structures, where small fluctuations in prices have a different effect from large shocks. Efficient Bayesian sequential computation is developed and implemented to estimate this effect in a practical, on-line manner. Examining 615 stocks that comprise the S\&P500 and Nikkei 225, we find that relaxing the linear assumption to our proposed nonlinear leverage effect function improves predictive performances for 89\% of all stocks compared to the conventional model assumption.

q-fin.ST↗

arXiv2016

Fully Parallel Particle Learning for GPGPUs and Other Parallel Devices

We develop a novel parallel resampling algorithm for fully parallelized particle filters, which is designed with GPUs (graphics processing units) or similar parallel computing devices in mind. With our new algorithm, a full cycle of particle filtering (computing the value of the likelihood for each particle, constructing the cumulative distribution function (CDF) for resampling, resampling the particles with the CDF, and propagating new particles for the next cycle) can be executed in a massively and completely parallel manner. One of the advantages of our algorithm is that every single numerical computation or memory access related to the particle filtering is executed solely inside the GPU in parallel, and no data transfer between the GPU's device memory and the CPU's host memory occurs unless for further processing, so that it can circumvent the limited memory bandwidth between the GPU and the CPU. To demonstrate the advantage of our parallel algorithm, we conducted a Monte Carlo experiment in which we apply the parallel algorithm as well as conventional sequential algorithms for estimation of a simple state space model via particle learning, and compare them in terms of execution time. The results show that the parallel algorithm is far superior to the sequential algorithm.

stat.CO↗