CBIT Advanced Award in Data Science (Level 7) with Integrated Real-world Experience

The projects are carefully designed to immerse students in real-world data science challenges. Each project aims to develop your technical expertise, analytical thinking, and teamwork abilities in a professional data science environment.
Examples of projects include:

Air Quality Index (AQI) Prediction Project

This project focuses on analysing and predicting air quality trends using real-world data. Learners will use advanced tools such as Python, Pandas, BeautifulSoup, Matplotlib, and Seaborn to clean, process, and visualise air quality data. The project also involves creating predictive models using the Air Quality Data.

Tech Stack

Key Learning Outcomes

• Analysing environmental datasets using time series analysis.
• Cleaning and preprocessing data.
• Developing predictive models using machine learning techniques.
• Visualising trends in using Python libraries.

Water Quality Analysis Project

This project involves analysing groundwater quality, utilising Python, Jupyter Notebook, Pandas, Matplotlib, Seaborn, and GeoPandas to conduct geospatial analysis, data cleaning, and visualisation. Learners will work with the Groundwater Quality Dataset.

Tech Stack

Key Learning Outcomes

• Performing data cleaning and preprocessing on large datasets.
• Conducting geospatial analysis to visualise regional differences.
• Applying descriptive statistics and parameter-specific analysis.
• Creating informative visualisations of findings.

Electricity Generation Analysis & Prediction Project

This project immerses learners in exploring historical power‐production data to uncover generation patterns and build forecasting models. Learners will clean and preprocess time‐series datasets, engineer features, and deploy predictive dashboards.

Tech Stack

Key Learning Outcomes

• Applying data‐cleaning techniques to large time‐series datasets
• Conducting exploratory analysis to identify generation trends
• Building and evaluating time‐series forecasting models
• Visualising model forecasts and confidence intervals
• Writing professional reports and documenting model assumptions

Healthcare Data Analysis Project

Learners analyse publicly available health‐system datasets to assess facility distribution, patient loads, and regional disparities. The project emphasises scalable data processing using Spark and creating interactive visualisations.

Tech Stack

Key Learning Outcomes

• Configuring and tuning PySpark clusters for big‐data workloads
• Handling missing values and inconsistent coding in healthcare records
• Applying clustering to group facilities by utilisation
• Using classification methods to predict facility performance tiers
• Optimising Spark jobs with caching, partitioning, and broadcast variables
• Delivering insights through visualisation nd clear reporting

COVID-19 Case Study Analysis Project

In this multifaceted case study, learners investigate a selected country’s pandemic trajectory through comprehensive data wrangling, merging multiple sources, and demographic analyses.

Tech Stack

Key Learning Outcomes

• Transforming raw COVID-19 case and vaccination datasets for analysis
• Merging multiple dataset seamlessly
• Visualising trends and demographics.
• Computing rolling averages, growth rates, and reproduction numbers
• Leveraging Pandas and NumPy for statistical summarisation
• Presenting data-driven findings in clear, narrative-driven reports

Stock Market Quantitative Analysis & Algorithmic Trading Project

This project introduces learners to quantitative finance by designing, back-testing, and evaluating algorithmic trading strategies using historical market data.

Tech Stack

Key Learning Outcomes

• Preprocessing price and volume data for financial modeling
• Engineering technical indicators (e.g., RSI, MACD, moving averages)
• Developing machine-learning models to signal trade opportunities
• Implementing back-testing frameworks to simulate strategy performance
• Evaluating risk-adjusted returns

The project follows a structured workflow mirroring real-world teams:

• Data Collection and Preparation: Acquire datasets through web scraping, APIs, and public data portals. Clean, standardise, and validate data using Python, Pandas, and PySpark.
• Exploratory Data Analysis (EDA): Perform statistical profiling and visual exploration using Matplotlib, Seaborn, and GeoPandas to identify trends, correlations, and data quality issues.
• Feature Engineering and Model Development: Engineer domain-specific features and train suitable models for forecasting, classification, clustering, and predictive analysis.
• Scalable and Geospatial Analysis: Apply PySpark for large-scale data processing and perform geospatial analysis to evaluate regional patterns and disparities.
• Model Evaluation and Refinement: Evaluate models using appropriate metrics, conduct tuning, and refine approaches for robustness and accuracy.
• Insights Generation, Reporting, and Deployment: Build dashboards, write professional reports, package notebooks and applications, and present findings in a simulated industry review.

During the programme, learners will assume various roles:

• Data Analyst: Perform data cleaning, EDA, and visualisation to extract actionable insights.
• Data Engineer: Collect, transform, and structure datasets, ensuring data quality and scalability.
• Machine Learning Engineer: Build, evaluate, and optimise predictive and classification models.
• Data Visualisation Specialist: Design dashboards and visual assets to communicate insights to non-technical stakeholders.

The programme evaluation ensures learners acquire both practical and theoretical knowledge necessary for professional success.

• Hacker Rank & Stack Overflow: Achieve a score above 1000 on Hacker Rank and contribute at least 10 answers on Stack Overflow.
• Project Involvement: Actively participate in projects and implement CI/CD processes for hosting.
• Behaviour and Attendance: Maintain punctuality, consistent attendance, and active session participation.
• GitHub Maintenance: Create and maintain repositories for projects and session topics.
• Community Engagement: Participate in programming communities on Slack and Discord to expand networks and collaboration skills.
• Communication Skills: Demonstrate effective written and verbal communication.
• Professionalism & Attitude: Show reliability, a positive demeanour, and strong work ethic.
• Quality of Work: Deliver accurate, thorough, and high-standard results for all tasks and projects.

Theoretical Assessments

Learners also complete written assignments, reports, or mini projects through the VisionEd portal. These submissions are assessed by tutors, complementing the practical project experience.