Turning Data Into Insights That Drive Decisions

Litsepiso Kose | Aspiring Data Analyst | BSc Computer Science (University of Western Cape)

About Me

I lived in the Free State for most of my life before moving to the Western Cape to pursue a Bachelor of Science in Computer Science at the University of the Western Cape. At first, I felt overwhelmed by the many career paths available in the tech world. Then I discovered data analysis — and I was hooked. It spoke to my logical side and love for solving real-world problems using evidence and structure.

In a nutshell, data just excites me. I love that it’s about making decisions based on real numbers — not emotions, beliefs, or assumptions. I want to be that numbers person in your company — the one who brings clarity through facts and helps you make confident, data-driven decisions.

Education

BSc in Computer Science – University of the Western Cape (February 2021–May 2025)

Skills

Python & R

For data analysis, machine learning, and automation.


Data Cleaning & Visualization

Turning raw data into clean, visual insights.

SQL & Database Design

To extract, clean, and manipulate structured data efficiently.

Communication & Problem Solving

Clearly presenting findings and solving real-world problems with data.

Power BI & Excel

For dashboards, interactive reports, and financial modeling.

Willing to Learn & Teamwork

Eager to grow and explore new tools, while working effectively with others to solve problems and achieve shared goals.

Projects

Python

Excel

SQL

Python – Exploratory Analysis of Credit Card Fraud Patterns

Tech Stack: Python, Pandas, Seaborn, Matplotlib

Description:
Performed an in-depth exploratory data analysis (EDA) on the Kaggle Credit Card Fraud Detection dataset to uncover patterns and anomalies in transaction behavior. Analyzed transaction times, amounts, and correlations between anonymized features. Compared statistical summaries of fraudulent vs. non-fraudulent transactions. Used visualizations like box plots, heatmaps, and histograms to highlight skewed distributions, outliers, and unusual activity times commonly associated with fraud.

 

Excel – E-Commerce Sales Dashboard

Tech Stack: Microsoft Excel, Pivot Tables, Power Query

Description:
Created an interactive dashboard using data similar to the Global Superstore dataset. Cleaned and transformed raw sales data using Power Query. Built pivot tables and slicers for filtering by region, product category, and customer segment. Included KPIs like total revenue, average order value, and monthly sales trends using data bars and line charts.

 

SQL – Inventory Management Reporting

Tech Stack: MySQL

Description:
Developed SQL queries for reporting on product stock levels using a custom schema inspired by the Walmart Sales dataset. Wrote joins across Products, Suppliers, and Warehouses tables. Identified low-stock items, generated reorder alerts, and summarized monthly incoming and outgoing stock using aggregation and CASE logic.

 

Python – Twitter Sentiment Analysis

Tech Stack: Python, NLTK, Scikit-learn, Twitter Dataset

Description:
Performed sentiment analysis on airline-related tweets using the Twitter US Airline Sentiment dataset. Preprocessed tweets with tokenization, stopword removal, and lemmatization. Built a classifier using Naive Bayes and evaluated performance with cross-validation. Plotted sentiment distribution and keyword frequency across different airlines.

Excel – HR Analytics Pivot Table Dashboard

Tech Stack: Microsoft Excel, Pivot Tables, Power Query, Charts

Description:
Developed an interactive HR dashboard using pivot tables and Excel’s data modeling tools. Cleaned and organized employee data including departments, job roles, performance ratings, and attrition status using Power Query. Created pivot tables to analyze employee headcount by department, gender distribution, average age by role, and attrition trends. Used slicers for filtering by location and job level. Included pivot charts to visualize employee retention rates and performance score distribution.

SQL – Customer Segmentation & Lifetime Value

Tech Stack: MySQL / PostgreSQL

Description:
Analyzed customer behavior from a transactional sales dataset. Used SQL window functions to calculate purchase frequency, average order value, and customer lifetime value. Segmented customers into tiers using CASE and RFM scoring. Delivered insights to guide marketing personalization and retention strategies.

 

Experience

Calculus 1 Tutor
University of the Western Cape · 2022 – 2024

  • Tutored first-year students in foundational calculus concepts.

  • Helped improve student performance through 1-on-1 sessions and group workshops.

  • Developed clear communication and problem-solving skills while simplifying complex topics.

Assistant Manager 
Mercy Tombstone Seasonal Role · 2021 – 2024

  • Assisted with store operations during school holidays, managing staff and customer service.

  • Gained hands-on experience in scheduling, inventory checks, and conflict resolution.

  • Strengthened leadership and team collaboration under pressure.

Relevant Coursework

Database Systems

  • Relational Model concepts and principles

  • Database system architecture representation

  • Relational database design and implementation

  • File systems vs. databases

  • Database modeling and design principles

  • Normalization techniques

  • SQL (Structured Query Language)

Machine Learning

  • Linear and logistic regression

  • Regularization methods

  • Neural networks

  • Support Vector Machines (SVM)

  • Application of regression techniques on real datasets

  • Implementation of neural networks and SVMs in analysis

Artificial Intelligence

  • Agent-based approach to problem-solving

  • Implementation of uninformed and informed search algorithms

  • Use of local and adversarial search strategies

  • Understanding and applying logical agents

Advanced Inference & Linear Models

  • Estimation using advanced linear models

  • Analysis of variance and multivariate regression

  • Designing and executing data analysis using statistical software

  • Writing analytical reports with interpreted results

Multivariate Distribution Theory

  • Discrete and continuous multivariate distributions

  • Limit theorems and asymptotic theory

  • Advanced estimation and hypothesis testing

  • Statistical programming and simulation techniques