arXiv subjects

Abeyankar Giridharan

Publications and source records attributed to Abeyankar Giridharan.

3 recordsLinked to original sources

arXiv2026

Fear Moves Markets: Sentiment-Augmented POMP for Volatility Modeling of Bitcoin Returns

Cryptocurrency markets exhibit extreme price swings and sentiment-driven regime shifts, which traditional volatility models often fail to capture. To address this, we develop a partially observed Markov processes (POMP) model augmented with sentiment and heavy-tailed distributions. Specifically, we extend Breto's framework by including the Fear and Greed Index (FGI) as an exogenous regressor in the latent volatility dynamics and replacing Gaussian measurement noise with a Student's t distribution. We fit the model via simulation-based inference using daily Bitcoin returns and FGI data from January 2020 to April 2025. Our approach significantly outperforms three benchmark models in log-likelihood and filter stability. Moreover, our model yields interpretable parameters consistent with known features of financial volatility. These results demonstrate that incorporating sentiment signals and heavy-tailed noise improves the modeling of volatility and regime shifts in cryptocurrency markets.

stat.AP↗

arXiv2025

Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection

With an ever-increasing availability of data, it has become more and more challenging to select and label appropriate samples for the training of machine learning models. It is especially difficult to detect long-tail classes of interest in large amounts of unlabeled data. This holds especially true for Intelligent Transportation Systems (ITS), where vehicle fleets and roadside perception systems generate an abundance of raw data. While industrial, proprietary data engines for such iterative data selection and model training processes exist, researchers and the open-source community suffer from a lack of an openly available system. We present the Mcity Data Engine, which provides modules for the complete data-based development cycle, beginning at the data acquisition phase and ending at the model deployment stage. The Mcity Data Engine focuses on rare and novel classes through an open-vocabulary data selection process. All code is publicly available on GitHub under an MIT license: https://github.com/mcity/mcity_data_engine

cs.CV↗

arXiv2025

Towards Precision Oncology: Predicting Mortality and Relapse-Free Survival in Head and Neck Cancer Using Clinical Data

Head and neck squamous cell carcinoma (HNSCC) presents significant challenges in clinical oncology due to its heterogeneity and high mortality rates. This study aims to leverage clinical data and machine learning (ML) principles to predict key outcomes for HNSCC patients: mortality, and relapse-free survival. Utilizing data sourced from the Cancer Imaging Archive, an extensive pipeline was implemented to ensure robust model training and evaluation. Ensemble and individual classifiers, including XGBoost, Random Forest, and Support Vectors, were employed to develop predictive models. The study identified key clinical features influencing HNSCC mortality outcomes and achieved predictive accuracy and ROC-AUC values exceeding 90\% across tasks. Support Vector Machine strongly excelled in relapse-free survival, with an recall value of 0.99 and precision of 0.97. Key clinical features including loco-regional control, smoking and treatment type, were identified as critical predictors of patient outcomes. This study underscores the medical impact of using ML-driven insights to refine prognostic accuracy and optimize personalized treatment strategies in HNSCC.

q-bio.QM↗