Daniel de las Heras Garcia
Portfolio
My Profile:
Skills:
Python (NumPy, Pandas, Scikit-learn, TensorFlow), SQL, MATLAB, R, LaTeX (advanced), Microsoft Office Suite (advanced), Java (intermediate), Hypotheisis Testing, Stochastic Processes.
Languages:
- Spanish Native
- English Bilingual - Proficient
Education
MSc Applied Mathematics and Data Science | Adelphi University, New York (May 2024)
Relevant modules: Regression Analysis, Applied Machine Learning, Advance Business Analytics, Simulations and Stochastic Processes, Database Management Systems, Statistical Consulting Practicum, Numerical Methods and Deterministic Models
| BSc Mathematics, Minor Statistics and Data Analytics | Adelphi University, New York (May 2023) |
Dean’s List for Academic Excellence (2019, 2020, 2021, 2022, 2023), Men’s Soccer Scholarship, NE10 Academic Honor Roll - Academic Distinction (2019, 2020, 2021, 2022, 2023), NE10 Academic Honor Roll - Academic Honors (2022)
Experience
Consulting Analyst
Confidential Financial Institution | Jan 2024 - May 2024
- Collaborated with a consultant team to develop approaches for categorizing customer transactions within a financial institution.
- Employed transaction categorization-based cadence and evaluated dollar transactions’ frequency, consistency, and predictability.
- Analyzed and extracted historical transaction big data to enhance customer financial behavior prediction accuracy.
Mathematical Consultant
Catholic Health | Jan 2024 - May 2024 • Developed and implemented techniques to design surveys and assess responses for identifying food insecurity among customers. • Aggregated different classification algorithms including XGBoost, logistic regression, and decision trees, to analyze survey data. • Applied hyperparameter tuning to address complexities of highly unbalanced classes in datasets and drive optimal outcomes. • Employed Jaccard score to measure similarities between affirmative response data across different survey questions.
Prospect Customers Billing Forecasting
Netrality Data Centers – Adelphi University | August 2023– May 2024
- Forecasted companies for revenue maximization using machine learning techniques.
- Developed, trained, and evaluated a machine learning model using a dataset of current companies, leveraging five classification algorithms: Logistic Regression, K-nearest neighbors, Random Forest, Gradient Boost, and LBGM.
- Collaborated with a five-person tea
- Find the project clicking on the links below:
| Project Paper | Project Files and Code |
Statistical Consultor
Hiatus App - Adelphi University | August 2023 – December 2023
- Developed a Marketing Mix Model (MMM) using data analytics techniques to optimize budget allocation for media channels.
- Implemented Lasso and Ridge Regression algorithms to build a predictive model and deliver actionable insights for strategic decision-making.
- Utilized Python programming for data preprocessing, model deployment, creating a scalable and efficient solution.
- Collaborated with the team to ensure alignment with business goals, meet deadlines, and deliver presentations to stakeholders.
| Guide | Project Files and Code |
Research - Fellowship (Department of Mathematics and Computer Science)
Adelphi University | August 2020 – May 2021
- Research and developed winning strategy algorithms in Graph and Game Theory in a 3-person team.
- Presented team results at the Mathematical Association of America Metro New York conference (May 1st, 2021) and Adelphi’s Annual Conference (May 10th, 2021).
Projects
Undergraduate Thesis: Stochastic Processes and Financial Applications
Stock Prices Modelling and Black and Sholes
Adelphi University
- Conducted in-depth research on Stochastic Processes, focusing on understanding concepts like Ito integration and its applications in finance, particularly in stock pricing and options.
- Developed a solid foundation in Stochastic Processes, essential for comprehending complex financial models.
- Explored concepts such as Random Walk, Markov Chain, Brownian motion, and Ito Integration, utilizing them to model stock prices and derive The Black and Scholes Equation.
- Implemented computer-programmed simulations to validate theoretical findings and enhance understanding.
- Derived The Black and Scholes Equation, showcasing proficiency in advanced mathematical modeling and its relevance in financial analysis.
| Project Paper | Project Files and Code |
Partisan Gerrymandering and MCMC Algorithm
Adelphi University
- Investigated partisan gerrymandering and how it impacts fair representation in elections.
- Explored historical and modern techniques of gerrymandering, and the utalization technological advancements and demographic data to enhance this district manipulation.
- Proposed a Monte Carlo Markov Chain (MCMC) algorithm to uniformly sample possible election district plans, enabling the assessment of gerrymandering probabilities.
- Developed an algorithmic framework for sampling diverse plans through transitions from an initial map, facilitating objective evaluations of gerrymandering potential.
- Implemented the MCMC algorithm to analyze the probability of obtaining specific district maps, contributing to the detection and prevention of unfair electoral practices.
| Project Final Paper | Project Files and Code |