PyTorchKR Papers

최신 논문

총 95편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2108.03190

Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series

We propose a quantum algorithm for sampling from a solution of stochastic differential equations (SDEs). Using differentiable quantum circuits (DQCs) with a feature map encoding of latent variables, we represent the quantile function for an underlying probability distribution and extract samples as DQC expectation values. Using quantile mechanics we propagate the system in time, thereby allowing for time-series generation. We test the method by simulating the Ornstein-Uhlenbeck process and sampling at times different from the initial point, as required in financial analysis and dataset augmentation. Additionally, we analyse continuous quantum generative adversarial networks (qGANs), and show that they represent quantile functions with a modified (reordered) shape that impedes their efficient time-propagation. Our results shed light on the connection between quantum quantile mechanics (QQM) and qGANs for SDE-based distributions, and point the importance of differential constraints for model training, analogously with the recent success of physics informed neural networks.

arXiv:2107.06460

A Unified Formula of the Optimal Portfolio for Piecewise Hyperbolic Absolute Risk Aversion Utilities

We propose a general family of piecewise hyperbolic absolute risk aversion (PHARA) utilities, including many classic and non-standard utilities as examples. A typical application is the composition of a HARA preference and a piecewise linear payoff in asset allocation. We derive a unified closed-form formula of the optimal portfolio, which is a four-term division. The formula has clear economic meanings, reflecting the behavior of risk aversion, risk seeking, loss aversion and first-order risk aversion. We conduct a general asymptotic analysis to the optimal portfolio, which directly serves as an analytical tool for financial analysis. We compare this PHARA portfolio with those of other utility families both analytically and numerically. One main finding is that risk-taking behaviors are greatly increased by non-concavity and reduced by non-differentiability of the PHARA utility. Finally, we use financial data to test the performance of the PHARA portfolio in the market.

arXiv:2102.09049

Efficient Reservoir Computing using Field Programmable Gate Array and Electro-optic Modulation

We experimentally demonstrate a hybrid reservoir computing system consisting of an electro-optic modulator and field programmable gate array (FPGA). It implements delay lines and filters digitally for flexible dynamics and high connectivity, while supporting a large number of reservoir nodes. To evaluate the system's performance and versatility, three benchmark tests are performed. The first is the 10th order Nonlinear Auto-Regressive Moving Average test (NARMA-10), where the predictions of 1000 and 25,000 steps yield impressively low normalized root mean square errors (NRMSE's) of 0.142 and 0.148, respectively. Such accurate predictions over into the far future speak to its capability of large sample size processing, as enabled by the present hybrid design. The second is the Santa Fe laser data prediction, where a normalized mean square error (NMSE) of 6.73x10-3 is demonstrated. The third is the isolate spoken digit recognition, with a word error rate close to 0.34%. Accurate, versatile, flexibly reconfigurable, and capable of long-term prediction, this reservoir computing system could find a wealth of impactful applications in real-time information processing, weather forecasting, and financial analysis.

arXiv:2102.07736

Network of Tensor Time Series

Co-evolving time series appears in a multitude of applications such as environmental monitoring, financial analysis, and smart transportation. This paper aims to address the following challenges, including (C1) how to incorporate explicit relationship networks of the time series; (C2) how to model the implicit relationship of the temporal dynamics. We propose a novel model called Network of Tensor Time Series, which is comprised of two modules, including Tensor Graph Convolutional Network (TGCN) and Tensor Recurrent Neural Network (TRNN). TGCN tackles the first challenge by generalizing Graph Convolutional Network (GCN) for flat graphs to tensor graphs, which captures the synergy between multiple graphs associated with the tensors. TRNN leverages tensor decomposition to model the implicit relationships among co-evolving time series. The experimental results on five real-world datasets demonstrate the efficacy of the proposed method.

arXiv:2101.04480

Text analysis in financial disclosures

Financial disclosure analysis and Knowledge extraction is an important financial analysis problem. Prevailing methods depend predominantly on quantitative ratios and techniques, which suffer from limitations like window dressing and past focus. Most of the information in a firm's financial disclosures is in unstructured text and contains valuable information about its health. Humans and machines fail to analyze it satisfactorily due to the enormous volume and unstructured nature, respectively. Researchers have started analyzing text content in disclosures recently. This paper covers the previous work in unstructured data analysis in Finance and Accounting. It also explores the state of art methods in computational linguistics and reviews the current methodologies in Natural Language Processing (NLP). Specifically, it focuses on research related to text source, linguistic attributes, firm attributes, and mathematical models employed in the text analysis approach. This work contributes to disclosure analysis methods by highlighting the limitations of the current focus on sentiment metrics and highlighting broader future research areas

arXiv:1811.10195

Bull Bear Balance: A Cluster Analysis of Socially Informed Financial Volatility

Using a method rooted in information theory, we present results that have identified a large set of stocks for which social media can be informative regarding financial volatility. By clustering stocks based on the joint feature sets of social and financial variables, our research provides an important contribution by characterizing the conditions in which social media signals can lead financial volatility. The results indicate that social media is most informative about financial market volatility when the ratio of bullish to bearish sentiment is high, even when the number of messages is low. The robustness of these findings is verified across 500 stocks from both NYSE and NASDAQ exchanges. The reported results are reproducible via an open-source library for social-financial analysis made freely available.

arXiv:1801.04841

Demographic Modeling Via 3-dimensional Markov Chains

This article presents a new model for demographic simulation which can be used to forecast and estimate the number of people in pension funds (contributors and retirees) as well as workers in a public institution. Furthermore, the model introduces opportunities to quantify the financial ows coming from future populations such as salaries, contributions, salary supplements, employer contribution to savings/pensions, among others. The implementation of this probabilistic model will be of great value in the actuarial toolbox, increasing the reliability of the estimations as well as allowing deeper demographic and financial analysis given the reach of the model. We introduce the mathematical model, its first moments, and how to adjust the required probabilities, showing at the end an example where the model was applied to a public institution with real data.

arXiv:1908.03748

Show Me Your Account: Detecting MMORPG Game Bot Leveraging Financial Analysis with LSTM

With the rapid growth of MMORPG market, game bot detection has become an essential task for maintaining stable in-game ecosystem. To classify bots from normal users, detection methods are proposed in both game client and server-side. Among various classification methods, data mining method in server-side captured unique characteristics of bots efficiently. For features used in data mining, behavioral and social actions of character are analyzed with numerous algorithms. However, bot developers can evade the previous detection methods by changing bot's activities continuously. Eventually, overall maintenance cost increases because the selected features need to be updated along with the change of bot's behavior. To overcome this limitation, we propose improved bot detection method with financial analysis. As bot's activity absolutely necessitates the change of financial status, analyzing financial fluctuation effectively captures bots as a key feature. We trained and tested model with actual data of Aion, a leading MMORPG in Asia. Leveraging that LSTM efficiently recognizes time-series movement of data, we achieved meaningful detection performance. Further on this model, we expect sustainable bot detection system in the near future.

arXiv:1907.10407

Evaluating the Effectiveness of Common Technical Trading Models

How effective are the most common trading models? The answer may help investors realize upsides to using each model, act as a segue for investors into more complex financial analysis and machine learning, and to increase financial literacy amongst students. Creating original versions of popular models, like linear regression, K-Nearest Neighbor, and moving average crossovers, we can test how each model performs on the most popular stocks and largest indexes. With the results for each, we can compare the models, and understand which model reliably increases performance. The trials showed that while all three models reduced losses on stocks with strong overall downward trends, the two machine learning models did not work as well to increase profits. Moving averages crossovers outperformed a continuous investment every time, although did result in a more volatile investment as well. Furthermore, once finished creating the program that implements moving average crossover, what are the optimal periods to use? A massive test consisting of 169,880 trials, showed the best periods to use to increase investment performance (5,10) and to decrease volatility (33,44). In addition, the data showed numerous trends such as a smaller short SMA period is accompanied by higher performance. Plotting volatility against performance shows that the high risk, high reward saying holds true and shows that for investments, as the volatility increases so does its performance.

arXiv:1809.05356

Numeral Understanding in Financial Tweets for Fine-grained Crowd-based Forecasting

Numerals that contain much information in financial documents are crucial for financial decision making. They play different roles in financial analysis processes. This paper is aimed at understanding the meanings of numerals in financial tweets for fine-grained crowd-based forecasting. We propose a taxonomy that classifies the numerals in financial tweets into 7 categories, and further extend some of these categories into several subcategories. Neural network-based models with word and character-level encoders are proposed for 7-way classification and 17-way classification. We perform backtest to confirm the effectiveness of the numeric opinions made by the crowd. This work is the first attempt to understand numerals in financial social media data, and we provide the first comparison of fine-grained opinion of individual investors and analysts based on their forecast price. The numeral corpus used in our experiments, called FinNum 1.0 , is available for research purposes.

arXiv:1807.09358

An Approximation Algorithm for Risk-averse Submodular Optimization

We study the problem of incorporating risk while making combinatorial decisions under uncertainty. We formulate a discrete submodular maximization problem for selecting a set using Conditional-Value-at-Risk (CVaR), a risk metric commonly used in financial analysis. While CVaR has recently been used in optimization of linear cost functions in robotics, we take the first stages towards extending this to discrete submodular optimization and provide several positive results. Specifically, we propose the Sequential Greedy Algorithm that provides an approximation guarantee on finding the maxima of the CVaR cost function under a matroidal constraint. The approximation guarantee shows that the solution produced by our algorithm is within a constant factor of the optimal and an additive term that depends on the optimal. Our analysis uses the curvature of the submodular set function, and proves that the algorithm runs in polynomial time. This formulates a number of combinatorial optimization problems that appear in robotics. We use two such problems, vehicle assignment under uncertainty for mobility-on-demand and sensor selection with failures for environmental monitoring, as case studies to demonstrate the efficacy of our formulation.

arXiv:1511.09123

A Short Survey on Data Clustering Algorithms

With rapidly increasing data, clustering algorithms are important tools for data analytics in modern research. They have been successfully applied to a wide range of domains; for instance, bioinformatics, speech recognition, and financial analysis. Formally speaking, given a set of data instances, a clustering algorithm is expected to divide the set of data instances into the subsets which maximize the intra-subset similarity and inter-subset dissimilarity, where a similarity measure is defined beforehand. In this work, the state-of-the-arts clustering algorithms are reviewed from design concept to methodology; Different clustering paradigms are discussed. Advanced clustering algorithms are also discussed. After that, the existing clustering evaluation metrics are reviewed. A summary with future insights is provided at the end.

arXiv:2606.29799v1cs.AI

The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models

This project introduces the CRISTAL Method (Coherent Reliable Intentional Synthesis of Truthful Analysis Logic), a neurosymbolic framework for automating complex analysis workflows, with fundamental investment analysis as a primary use case. This domain poses major challenges: high structural uncertainty, noisy and subjective data, tight attention budgets, and the need for justified, reproducible decisions. Human analysts often struggle in this domain due to cognitive biases and limitations, suggesting significant value in automation. But while LLM-based agents have been proposed as analytical aids, their limitations -- poor numerical reasoning, unawareness of uncertainty, and lack of reproducibility -- hinder their effectiveness in this context. CRISTAL addresses these gaps through a principled blend of statistical model synthesis, continuous learning, and active learning. Starting from a natural-language prior knowledge curriculum, CRISTAL builds a dynamic, interpretable probabilistic program that enables full Bayesian inference, including uncertainty quantification and budget-aware data acquisition. CRISTAL continually refines its world model during analysis, leveraging LLMs for code synthesis and learning. We validate CRISTAL on a novel benchmark of synthetic equities with rich financial and textual data. On a company classification task, CRISTAL achieves Bayes-optimal accuracy with just 5 examples and a 5-second budget, outperforming state-of-the-art LLMs that plateau around 40\% accuracy even with order-of-magnitude more input data and compute.

arXiv:2606.29251v1cs.AI

When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis

Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they can alter the investment judgment supported by the original source. We frame this problem as information fidelity: compression loses fidelity when it changes the decision induced by the source. In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process. Across financial filings and earnings-call transcripts, we find that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions. We analyze two diagnostic patterns associated with fidelity loss: decontextualization, where salient evidence is retained but separated from the caveats and contextual qualifiers needed for correct interpretation, and model dependency, where different compressors expose different views of the same source. We then propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source. Our results suggest that financial compression should be evaluated not only by efficiency or factuality, but also by its ability to preserve decision-relevant context.

arXiv:2606.23032v1cs.AI

IPO Finance Agent: Finance Agent v2를 넘어선 LLM 금융 애널리스트 평가와 자동화된 루브릭 생성 — SpaceX(SPCX) IPO 사례

IPO Finance Agent: Evaluation of LLM Financial Analysts beyond Finance Agent v2, with Automated Rubric Generation -- the Case of the SpaceX (SPCX) IPO

Finance Agent v2(Vals AI 개발)는 금융 태스크에서 Anthropic Claude와 OpenAI ChatGPT 프론티어 언어 모델을 평가하는 기준 벤치마크로 자리잡았다. 그러나 이 벤치마크는 공개 기업의 정기 보고서(SEC 10-K 및 10-Q 공시)만을 좁게 다루며, 에이전틱 하네스는 비정제 청크 검색에 의존한다. 태스크 설계와 검색 방식 모두 IPO 실사의 고유한 난제를 다루지 않는다. SEC S-1 공시는 과거 재무제표, 지배구조, 프로포마 및 공동지배 회계 처리, 자본 조달 서술, 인수 민감 위험 공시를 정기 공시보다 훨씬 긴 문서에 혼합하여 담고 있다. 이에 우리는 Finance Agent v2 프레임워크를 태스크 도메인과 검색 아키텍처 두 방향으로 확장한 IPO Finance Agent를 제안한다. 실험 과정에서 원본 Finance Agent v2 하네스는 문서 길이로 인해 SpaceX S-1 공시 관련 출력을 사실상 전혀 생성하지 못했다. 따라서 우리는 장문 문서에 더 현실적이고 산업 표준에 부합하는 방식인 컨텍스트 검색으로 에이전틱 하네스를 개선해야 했다. 또한 IPO 실사 질문 1,000건으로 구성된 데이터셋을 구축하고, 재현성 지원을 위해 SpaceX(SPCX) S-1 공시에 관한 70개 질문을 공개하였으며, 벤치마크 오염 방지를 위해 나머지는 비공개로 유지한다. 아울러 벤치마크 평가 루브릭을 자동 생성하는 평가자-옵티마이저 파이프라인을 도입한다. 각 질문에 대해 독립적으로 생성된 모델 답변 앙상블에서 후보 사실을 추출하고, 이를 초안 기준으로 통합한 뒤 누락, 환각, 등급 오분류, 중복을 자동 감사하며, LLM 피드백을 통해 반복 수정, 타겟 보강, 중복 제거를 수행한다. 인간 전문가는 배포 전 최종 루브릭만 검토한다. 결과에 따르면, 평가된 모델 중 최고 성능인 Alibaba Qwen 3.7 Max는 쿼리당 $0.30에 79.4% 정확도를 달성하며, Pareto 프론티어상 가장 비용 효율적인 모델인 Xiaomi MiMo-2.5 Pro는 쿼리당 $0.05에 소폭 낮은 정확도(76.8%)를 기록한다. 두 모델 모두 현재 Finance Agent v2 리더보드 최고점인 Google Gemini 3.5 Flash(쿼리당 $2.51에 57.9%)를 상회하며, 비용 효율 면에서는 FABv2 최저가 항목(MiniMax M3: $0.32에 48.3%)조차 밑돈다. 코드와 데이터는 GitHub(https://github.com/benstaf/ipoagent)에 공개되어 있다.