Find & Explore Verified Academic Research Journals

Words that Move Markets: Quantifying the Impact of RBI's Monetary Policy Communications on Indian Financial Market

This study examines how the Reserve Bank of India's (RBI) monetary policy communications influence the Indian financial market over the period from April 2014 to June 2024. The research integrates advanced Natural Language Processing (NLP) techniques with financial econometrics to analyze Monetary Policy Statements and RBI press conference transcripts. BERTopic is employed to identify major economic themes within RBI communications, while a fine-tuned RoBERTa model classifies sentiment into hawkish, dovish, and neutral categories. The study further estimates the dynamic effects of topic-specific sentiment on financial markets using Local Projection models. The findings reveal that market reactions vary significantly depending on both the subject and tone of RBI communications. Dovish sentiment associated with interest rate policy and economic growth generally corresponds with declines in equity markets, suggesting that investors often interpret accommodative language as a signal of economic weakness rather than policy support. Conversely, dovish communication regarding foreign exchange reserve management positively influences market performance. The research demonstrates that combining topic modeling with sentiment analysis provides a more comprehensive understanding of central bank communication strategies and their financial implications. These results contribute to the literature on monetary policy communication in emerging economies and offer practical insights for policymakers seeking more effective communication as well as investors interpreting policy signals.

Building Entity Association Mining Framework for Knowledge Discovery

This paper presents a domain-independent entity association mining framework designed to extract meaningful knowledge from large-scale unstructured textual data. The framework integrates document filtering, configurable entity extraction, and association mining to automate knowledge discovery across diverse business applications. It supports multiple entity extraction techniques, including DBpedia Spotlight, spaCy Named Entity Recognition, custom entity matchers, and dictionary-based phrase extraction, enabling flexible adaptation to different domains. The extracted entities are connected through co-occurrence relationships to construct knowledge graphs that reveal hidden associations, emerging trends, and thematic clusters. Additionally, the framework introduces a scoring mechanism to rank entity relationships and improve information retrieval and analytical decision-making. To demonstrate its practical utility, the proposed architecture is evaluated using two financial use cases: brand product discovery and vendor risk monitoring. Experimental results show that the framework effectively identifies relationships among entities, reduces duplicate development effort, and accelerates the deployment of text mining solutions. By combining semantic information with statistical co-occurrence analysis, the framework provides a scalable and reusable approach for generating actionable insights from large document collections. The authors conclude that the proposed system can serve as a foundational platform for future knowledge graph applications and advanced business intelligence systems across multiple industries.

Autograder+: A Multi-Faceted AI Framework for Rich Pedagogical Feedback in Programming Education

The rapid growth of programming education has outpaced traditional assessment tools, leaving faculty with limited means to provide meaningful, scalable feedback. Conventional autograders, while efficient, act as "black-box" systems that merely indicate pass/fail status, offering little instructional value or insight into the student's approach. Autograder+, a comprehensive and intelligent framework designed to evolve autograding from a summative evaluation tool into a formative learning platform, addresses this gap through two unique features: (1) feedback generation via a fine-tuned Large Language Model (LLM), and (2) visualization of all student code submissions. The LLM is adapted via domain-specific fine-tuning on curated student code and expert annotations, ensuring feedback is pedagogically aligned and context-aware. In empirical evaluation across 600 student submissions across various programming problems, Autograder+ produced feedback with an average BERTScore F1 of 0.7658, demonstrating strong semantic alignment with expert-written feedback. To make visualizations meaningful, Autograder+ employs contrastively learned embeddings trained on 1,000 annotated submissions, which organize solutions into a performance-aware semantic space resulting in clusters of functionally similar approaches. The framework also integrates a Prompt Pooling mechanism, allowing instructors to dynamically influence the LLM's feedback style using a curated set of specialized prompts. By combining advanced AI feedback generation, semantic organization, and visualization, Autograder+ reduces evaluation workload while empowering educators to deliver targeted instruction and foster resilient learning outcomes.

Reinforcing Competitive Multi-Agents for Playing 'So Long Sucker

This paper investigates the strategy game So Long Sucker (SLS) as a novel benchmark for multi-agent reinforcement learning (MARL). Unlike traditional board or video game testbeds, SLS is distinguished by its coalition formation, strategic deception, and dynamic elimination rules, making it a uniquely challenging environment for autonomous agents. We introduce the first publicly available computational framework for SLS, complete with a graphical user interface and benchmarking support for reinforcement learning algorithms. Using classical deep reinforcement learning methods (e.g., DQN, DDQN, and Dueling DQN), we train self-playing agents to learn the rules and basic strategies of SLS. Experimental results demonstrate that, although these agents achieve roughly half of the maximum attainable reward and consistently outperform random baselines, they require long training horizons (~2000 games) and still commit occasional illegal moves, highlighting both the promise and limitations of classical reinforcement learning. Our findings establish SLS as a negotiation-aware benchmark for MARL, opening avenues for future research that integrates game-theoretic reasoning, coalition-aware strategies, and advanced reinforcement learning architectures to better capture the social and adversarial dynamics of complex multi-agent games.

AdversaBench: Automated LLM Red-Teaming

Scaling adversarial evaluation of large language models requires two things at once: a way to generate hard inputs, and a way to confirm that the resulting failures are real. A single judge is fast, but it cannot tell you when it is being lenient, and it cannot resolve close calls on its own. We built ADVERSABENCH, an automated red-teaming pipeline and reliability study that mutates seed prompts with five structured operators, queries a weak target model, and confirms failures through a three-judge panel with a meta-judge tiebreaker. We report a study on 45 seeds (15 per category: reasoning, instruction-following, and tool use), expanded from an initial pilot of 30 to improve coverage of temporal reasoning, strict formatting constraints, and tool edge cases. Every seed produced a confirmed failure. Four results stood out. First, operator effectiveness varies sharply by category: inject_distractor scores 0.33 mean reward on instruction-following seeds but 1.00 on reasoning and tool-use. Second, binary failure rate hides difficulty: instruction-following seeds needed 2.4 attacker iterations on average versus 1.1 for reasoning and tool-use.

Generation and De-Identification of Indian Clinical Discharge Summaries using LLMs

The consequences of a healthcare data breach can be devastating for the patients, providers, and payers. The average financial impact of a data breach in recent months has been estimated to be close to USD 10 million. This is especially significant for healthcare organizations in India that are managing rapid digitization while still establishing data governance procedures that align with the letter and spirit of the law. Computer-based systems for de-identification of personal information are vulnerable to data drift, often rendering them ineffective in cross-institution settings. Therefore, a rigorous assessment of existing de-identification against local health datasets is imperative to support the safe adoption of digital health initiatives in India. Using a small set of de-identified patient discharge summaries provided by an Indian healthcare institution, in this paper, we report the nominal performance of de-identification algorithms (based on language models) trained on publicly available non-Indian datasets, pointing towards a lack of cross-institutional generalization. Similarly, experimentation with off-the-shelf de-identification systems reveals potential risks associated with the approach. To overcome data scarcity, we explore generating synthetic clinical reports (using publicly available and Indian summaries) by performing in-context learning over Large Language Models (LLMs). Our experiments demonstrate the use of generated reports as an effective strategy for creating high-performing de-identification systems with good generalization capabilities.

Anemia Vision: Non-Invasive Anemia Detection via Smartphone Imagery Using EfficientNet-B3 with TrivialAugmentWide, Mixup, and Persistent Patient History Management

Anemia affects over one billion people globally and remains severely under-diagnosed in low-resource regions where laboratory blood tests are inaccessible. This paper presents Anemia Vision, an end-to-end web-based system for non-invasive anemia screening from smartphone photographs of the palpebral conjunctiva and fingernail beds. The proposed pipeline fine-tunes a pre-trained EfficientNet-B3 backbone with a redesigned three-layer classifier head incorporating BatchNorm, GELU activations, and high-rate Dropout. Training employs four orthogonal accuracy-boosting techniques: TrivialAugment Wide for policy-free image augmentation, RandomErasing for spatial regularisation, Mixup ($\alpha=0.2$) for inter-class smoothing, and cosine-annealing scheduling with linear warmup. Early stopping is governed by peak validation accuracy rather than validation loss to prevent premature termination on high-variance epochs. The deployed Flask application integrates persistent patient-history management backed by PostgreSQL on Render, with an automated database-migration entrypoint ensuring zero data loss across redeploys. Experimental evaluation on a two-class (anemic / non-anemic) conjunctiva-fingernail dataset demonstrates a target validation accuracy of 94–97% and AUC-ROC of 0.97–0.99 under the full GPU training profile, compared with 45% validation accuracy and AUC-ROC of 0.58 achieved by the baseline three-epoch CPU-only training. The system is publicly accessible at https://anemia-detection-gbmj.onrender.com.

AI-Driven Diabetic Retinopathy Screening: Multicentric Validation of AIDRSS in India

Diabetic retinopathy (DR) is a major cause of vision loss, particularly in India, where access to retina specialists is limited in rural areas. This study aims to evaluate the Artificial Intelligence-based Diabetic Retinopathy Screening System (AIDRSS) for DR detection and prevalence assessment, addressing the growing need for scalable, automated screening solutions in resource-limited settings. Approach: A multicentric, cross-sectional study was conducted in Kolkata, India, involving 5,029 participants and 10,058 macula-centric retinal fundus images. The AIDRSS employed a deep learning algorithm with 50 million trainable parameters, integrated with Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing for enhanced image quality. DR was graded using the International Clinical Diabetic Retinopathy (ICDR) Scale, categorizing disease into five stages (DR0 to DR4). Statistical metrics including sensitivity, specificity, and prevalence rates were evaluated against expert retina specialist assessments. Results: The prevalence of DR in the general population was 13.7%, rising to 38.2% among individuals with elevated random blood glucose levels. The AIDRSS achieved an overall sensitivity of 92%, specificity of 88%, and 100% sensitivity for detecting referable DR (DR3 and DR4). These results demonstrate the system's robust performance in accurately identifying and grading DR in a diverse population. Conclusions: AIDRSS provides a reliable, scalable solution for early DR detection in resource-constrained environments. Its integration of advanced AI techniques ensures high diagnostic accuracy, with potential to significantly reduce the burden of diabetes-related vision loss in underserved regions.

Predictive Analysis of Tuberculosis Treatment Outcomes Using Machine Learning: A Karnataka TB Data Study at a ScalePredictive Analysis of Tuberculosis Treatment Outcomes Using Machine Learning: A Karnataka TB Data Study at a Scale

Tuberculosis (TB) remains a global health threat, ranking among the leading causes of mortality worldwide. In this context, machine learning (ML) has emerged as a transformative force, providing innovative solutions to the complexities associated with TB treatment. This study explores how machine learning, especially with tabular data, can be used to predict Tuberculosis (TB) treatment outcomes more accurately. It transforms this prediction task into a binary classification problem, generating risk scores from patient data sourced from NIKSHAY, India's national TB control program, which includes over 500,000 patient records. Data preprocessing is a critical component of the study, and the model achieved a recall of 98% and an AUC-ROC score of 0.95 on the validation set, which includes 20,000 patient records. We also explore the use of Natural Language Processing (NLP) for improved model learning. Our results, corroborated by various metrics and ablation studies, validate the effectiveness of our approach. The study concludes by discussing the potential ramifications of our research on TB eradication efforts and proposing potential avenues for future work. This study marks a significant stride in the battle against TB, showcasing the potential of machine learning in healthcare.

Age-Structured Epidemic Model under Vaccination with Vector Transmission

Dengue remains a major global public health concern due to its high morbidity and economic burden. Mathematical modeling is essential to understand its transmission mechanisms and for evaluating intervention strategies. In this paper, we formulate a vector-host model in which the human population is structured by age, and vaccinated individuals are further described by time since vaccination. The mosquito population is coupled to the host dynamics and reduced under a quasi-steady-state assumption. By integrating over vaccination age, we obtain a nonlinear steady-state formulation and express the endemic equilibrium as a fixed-point problem for the infected mosquito population. Using monotonicity arguments and the intermediate value theorem, we establish existence and uniqueness of the endemic equilibrium under a biologically interpretable threshold condition on the basic reproduction number. The analysis highlights the influence of age-dependent vaccination on long-term dengue dynamics.