Project

UK Road Safety Analysis, Aston University

project-1

Keywords: Pandas Numpy EDA Scikit-learn

I developed predictive models to classify accident severity using UK Road Safety data, aiming to enhance risk profiling for insurance premium assessments. The project involved cleaning and preprocessing over one million records using Python libraries such as Pandas and NumPy, resulting in 99% data accuracy and the successful removal of key outliers. I conducted exploratory data analysis (EDA) with Matplotlib and Seaborn to uncover meaningful patterns related to accident severity, including factors like vehicle type, driver age, and weather conditions. To build the predictive models, I applied several machine learning algorithms—Logistic Regression, Decision Trees, K-Nearest Neighbours, and Random Forest—using Scikit-learn. By implementing Random Undersampling with Cluster Centroids, I achieved an 82% accuracy rate in classifying minority ‘Fatal’ accident cases, significantly reducing misclassifications compared to models trained on unbalanced data.

Bank Marketing Campaign Analysis

project-2

Keywords: ETL DAX Power BI

I conducted a project aimed at identifying the key factors influencing a customer's likelihood to subscribe to a bank term deposit, while also evaluating the effectiveness of current and past direct marketing campaigns for a Portuguese banking institution. Throughout the project, I enhanced my ability to load, clean, and transform data using Power BI (Power Query). I leveraged DAX tools to calculate core performance metrics such as conversion rate and total clients, which supported the development of customer segmentation models for more targeted marketing efforts. Using Power BI, I built comprehensive and visually engaging reports to communicate insights and define optimal strategies for future marketing campaigns. The project presentation was well-received and earned the highest grade of 9 out of 10.

HR Analytics - Employee Attrition Analysis

project-2

Keywords: ETL DAX Power BI HR Analytics

I conducted an in-depth analysis of employee attrition for a company with 4,000 employees, focusing on understanding the key factors driving the 15% annual turnover rate. As part of the project, I developed interactive Power BI dashboards that visualized attrition trends, employee demographics, job satisfaction, work environment, and compensation, helping to identify critical drivers of employee retention. I processed and cleaned HR data to compute essential metrics such as total employees, attrition rate, and average monthly income. Using DAX, I calculated key indicators including the impact of tenure, job role distribution, and the influence of salary on retention. Through this analysis, I identified significant factors contributing to attrition—such as work-life balance, compensation levels, and satisfaction with the working environment. Based on these insights, I provided actionable, data-driven recommendations to support workforce planning, improve employee retention, and refine HR policies.

Blogs

Factors Influencing Second-Hand Car Prices: A Statistical Analysis

blog-1

Keywords: Linear regressions SPSS

Multiple linear regression is used to determine how mileage, age fuel type and colour affect variation in the second-hand car price in the UK. Additionally, the method produces significance of variables and measure of goodness of fit. The information gained from predicting car price based on selected factors could help business improve decision making by employing effective pricing strategies and marketing initiatives in dynamic nature of car market.

Predicting Customer Spending Behavior Using Logistic Regression

blog-2

Keywords: Logistic regression SPSS

The analysis indicates that customers who buy additional Value or Brand Products are more inclined to be classified as high spenders. The model achieved 95% accuracy but tended to correctly predict high spenders more frequently than low spenders. For Fresco, this insight guides targeted marketing initiatives towards high spenders, maximising high revenue potential.

Predicting UK Car Prices: A Machine Learning Approach to Optimised Pricing Strategies

blog-3

Keywords: Random Forest Neural Network K-NN

The project’s goal is to create a method for precise car pricing prediction. In addition to helping car company’s marketing team choose the best pricing tactics, the method also helps consumers make informed purchasing decisions and provides insightful information to car industry analysts. We meticulously selected significant car’s features such as transmission, safety, navigation,... to build this predictive method.

By considering a larger variety of factors, such as geographic and economic variables, a better foundation for prediction may be built, which will enhance the effectiveness of this technique. In order to maintain the resilience of the prediction model, it is advisable to incorporate a user feedback loop to employ rigorous validation techniques. It is imperative to maintain fairness and trust by considering any biases in model predictions and ethical considerations. When combined, these actions provide a thorough approach to developing a more accurate and reliable car price forecasting tool.

Experience

Mondelēz International

Position: Digital and Data Intern

July 2024 – July 2025

  • Streamline ETL processes and data transformation using Power Query Editor in Power BI, increasing data pipeline efficiency and reducing manual reporting time by 30%.
  • Build, automate, and maintain 10+ Power BI dashboards across 5+ reporting categories, delivering real-time insights to 30+ technical and non-technical stakeholders and accelerating data-driven decision-making.
  • Develop and own the Product Quality Benchmarking Dashboard, evaluating 130+ in-market products against quality benchmarks (on-strategy delivery, overall liking, and overall preference); insights informed operational decisions to better align with supply chain goals.
  • Produced 6+ Power BI reports on foreign material complaints; collaborated with cross-functional leaders to analyse root causes by product line and site, enabling targeted corrective actions (e.g., supplier checks, process audits) that reduced issue recurrence by 15% within 6 months.
  • Created and deployed a team culture survey platform (23 questions) using Power Apps with 85%+ participation rate; delivered data-driven insights that improved team culture scores by 15% in one quarter.

Vieunite UK Ltd

Position: Business Intelligence Analyst Intern

May 2024 – August 2024

  • Independently built and deployed 10+ real-time Power BI dashboards from scratch, integrating GA4, internal APIs, and manual Excel uploads to provide actionable website and social media insights to leadership.
  • Designed Tableau funnel dashboards to track process drop-offs and conversion barriers; delivered data-driven recommendations that improved operational efficiency and increased conversion rates by 10% in 2 months.
  • Identified trends in user behaviour, traffic sources, and engagement metrics (e.g., sessions, bounce rate), leading to a 20% increase in page views over 2 months by optimising website layout, updating key landing pages, and improving content relevance.
  • Collaborated with 5 marketing team members to run A/B test on social media content (e.g., CTAs and real-time updates); insights informed content strategy changes that increased site engagement by 15% and conversions by 10% over 3 months.

ABI Game Studio (ABI)

Position: Data Analyst Intern

June 2023 – September 2023

  • Designed 20+ interactive dashboards and reports for the company's flagship game using Microsoft Power BI, pulling data from multiple Excel files, each containing over 1,000,000 rows, delivering performance insights for cross-functional teams, such as product managers, game designers, and marketing managers.
  • Analysed player behaviour data using Firebase Analytics, tracking progression, game difficulty, ad interactions, and resource usage; implemented gameplay adjustments and reward tuning that boosted daily active users (DAU) and retention by 15% over 2 months.
  • Collaborated with the Data Analyst to calculate key metrics (e.g., average playtime, replays per chapter) using SQL Server with 95% accuracy.

Tien Phong Commercial Joint Stock Bank (TPBank)

Position: Data Analyst Intern

February 2023 – June 2023

  • Designed and executed robust SQL scripts to clean, validate, and structure 700+ customer transaction records—improving data quality for AI-driven fraud detection models and supporting credit risk analysis.
  • Led Python-based feature engineering using pandas and statsmodels on multi-source Excel datasets, improving classification performance for TPBank’s EVO Credit Card Fraud Detection system.

More

Education

Skills

Certifications

Elements

Text

This is bold and this is strong. This is italic and this is emphasized. This is superscript text and this is subscript text. This is underlined and this is code: for (;;) { ... }. Finally, this is a link.

Heading Level 2

Heading Level 3

Heading Level 4

Heading Level 5
Heading Level 6

Blockquote

Fringilla nisl. Donec accumsan interdum nisi, quis tincidunt felis sagittis eget tempus euismod. Vestibulum ante ipsum primis in faucibus vestibulum. Blandit adipiscing eu felis iaculis volutpat ac adipiscing accumsan faucibus. Vestibulum ante ipsum primis in faucibus lorem ipsum dolor sit amet nullam adipiscing eu felis.

Preformatted

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';

Lists

Unordered

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Alternate

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Ordered

  1. Dolor pulvinar etiam.
  2. Etiam vel felis viverra.
  3. Felis enim feugiat.
  4. Dolor pulvinar etiam.
  5. Etiam vel felis lorem.
  6. Felis enim et feugiat.

Icons

Actions

Table

Default

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Alternate

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Buttons

  • Disabled
  • Disabled

Form