Junior Data Scientist

I developed a machine learning solution to predict customer churn using a telecommunications customer dataset. I cleaned and prepared data with Pandas and NumPy, then explored patterns through Matplotlib and Seaborn visualisations.

I implemented and compared Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting classifiers. I evaluated performance with accuracy, precision, recall, F1-score, and cross-validation, analysed feature importance, and documented the complete workflow in a Jupyter Notebook.

I analysed 14,640 Twitter records relating to airline customer experiences and classified sentiment as positive, neutral, or negative. I applied NLP methods to clean and preprocess text data for machine learning classification.

I built multiclass sentiment classifiers using neural networks and XGBoost, with XGBoost achieving approximately 80% accuracy. I assessed class-level performance using precision, recall, and F1-score, and translated findings into business recommendations concerning customer service, flight delays, and passenger communication.

I collaborated in a five-person data science team to analyse 21,597 property records and identify factors influencing house prices for a property developer. The work covered data acquisition, cleaning, exploratory analysis, modelling, and interpretation.

I contributed to a baseline linear regression model and evaluated statistical significance using coefficients, p-values, and adjusted R-squared. I helped interpret the model outputs and turn analytical findings into actionable business recommendations.

I integrated data from multiple movie-industry sources, including box-office, ratings, reviews, and metadata, and queried an IMDb database using SQL. I performed data cleaning, preparation, and exploratory analysis using descriptive statistics, distributions, and correlation analysis.

I engineered features such as movie return on investment to investigate relationships among genre, budget, ratings, runtime, release period, and box-office performance. I delivered recommendations to support movie-production and investment decisions.

Bachelor of Science in Mechatronic Engineering.

Completed training in Python, SQL, data analysis, statistics, machine learning, NLP, time series, deep learning, PySpark, dashboards, cloud computing, MLOps, and large language models.

Completed the Data Science and Machine Learning: Making Data-Driven Decisions programme, earning 8 CEUs. Certificate issued in October 2024.