The research focuses on evaluating various classical machine learning algorithms for sentiment classification in financial texts. A publicly available dataset combining FIQA and Financial PhraseBank sources was used, containing over 5,800 labeled financial sentences. Data preprocessing steps included cleaning, tokenization, stopword removal, and lemmatization. Exploratory data analysis was conducted to understand sentiment distribution, text length patterns, and word frequencies.
Sentiment labels were encoded numerically to serve as target variables in classification models. A range of traditional machine learning algorithms was implemented and assessed to explore their suitability for sentiment analysis in the financial domain. Evaluation metrics including accuracy, precision, recall, and F1-score were used to assess model performance.
Preliminary results indicate that traditional machine learning models can effectively classify sentiment in financial texts, especially when supported by proper text preprocessing. Furthermore, integrating sentiment analysis with financial data shows potential for improving market forecasting accuracy.


This work contributes to the growing field of financial data science by demonstrating the effectiveness of NLP-driven sentiment analysis and offering a framework for building predictive systems that combine textual and numerical financial indicators.
]]> This project aims to predict the statistical performance of college basketball players upon entering the NBA by integrating structured data (rookie-year statistics) with unstructured data (text-based scouting reports). The proposed system applies NLP techniques to extract features from scouting narratives, focusing on player strengths, weaknesses, and comparisons. These textual features are combined with quantitative performance metrics to develop predictive models for key statistical categories such as points, assists, rebounds, blocks, and steals.
Clustering methods are further applied to group players with similar scouting profiles. Instead of labeling clusters as fixed archetypes, the approach emphasizes identifying the most comparable NBA players for each prospect. This similarity-based framework provides interpretability for scouting evaluations and a practical foundation for projecting performance. The predictive component then leverages historical outcomes of comparable players to generate forecasts for new prospects.


The results demonstrate that clustering can organize players into meaningful groups based on textual analysis, while the predictive framework produces reasonable estimates of rookie-year performance. Together, these findings highlight the potential of integrating NLP and ML into scouting workflows to complement traditional evaluation methods, reduce bias, and enhance the accuracy of performance projections.
]]> ]]> ]]> ]]> ]]> The analyzer has gone through several updates: CRAv2 set the foundation with Random Forest classifiers, CRAv3 took a semantic-first approach, and CRAv4 introduced a mixed strategy that fuses rules, semantic pattern analysis, and weighted confidence scoring. There was also an experimental Smart Repository Classifier (SRC) that tried to combine rule-based and machine-learning techniques, plus a side project that looked into detecting design patterns using AST embeddings and Code Property Graphs.
The system was trained on 122 repositories and tested on 47 others across seven different categories. The results were impressive: CRAv3 hit an overall accuracy of 26.4%, while CRAv4 shot up to 70%, with big improvements in web applications (+133%) and CLI tools (+45%). Even though Random Forest tests only maxed out at about 35% in some categories, CRAv4's hybrid method turned out to be both more accurate and easier to understand.
Some key hurdles included the lack of comprehensive datasets, issues with ASTMiner's dependencies, and the author's initial unfamiliarity with machine learning. Tackling these challenges taught valuable lessons in building datasets, feature engineering, and evaluating model

In summary, this project highlights the benefits of blending semantic, structural, and rule-based strategies to gauge developer skills. Looking ahead, plans involve expanding datasets, diving into deep learning for design pattern detection, and enhancing the analyzer into a more general code intelligence tool.
]]> The final ensemble achieved an overall accuracy of 76.8% and, critically, a recall of 73% for the churn class, demonstrating strong reliability in identifying at-risk individuals. A key deliverable is an interactive user interface allowing stakeholders to leverage model predictions, visualize churn trends, and interpret the key factors driving customer behavior. This study culminates in a predictive tool that provides actionable insights, enabling businesses to transition from a reactive to a proactive approach in managing customer relationships. By identifying at-risk customers, companies can deploy targeted interventions to enhance loyalty, reduce churn, and secure long-term profitability, creating a practical bridge between advanced analytics and strategic decision-making
]]> ]]> ]]> The aim of this project was to introduce a new solution to these issues: Lightfin, a fiscalization, loan and subsidy management system built with a microservice architecture, designed to offer enhanced performance, low delays, easy scalability and high stability.
]]> The MERN stack, which features MongoDB, Express, React and Node.js, together with Tailwind is used for development. The system features secure user authentication, featureful event management and filtering, event reviewing and rating, and intuitive user management.
Eventik eases the process of event searching, enhances event visibility, simplifies participation in events and supports a more connected community, something much needed today.
]]>