Semester Teaching Programme: Data Analysis and Machine Learning
Third-Year Bachelor's Degree in Marketing (Licence 3 Marketing) — Semester 5
1. General Information
|
Item |
Details |
|---|---|
|
Module title |
Data Analysis and Machine Learning |
|
Academic level |
Third-Year Bachelor's Degree (L3) |
|
Speciality |
Marketing |
|
Semester |
Semester 5 (S5) |
|
Teaching language |
English |
|
Module type |
Specialised module |
|
Main focus |
Marketing data analysis, statistical methods, predictive analytics and machine learning applications in marketing |
2. General Objective
The module aims to equip students with the theoretical knowledge and practical skills required to collect, prepare, analyse and interpret marketing data, and to introduce them to machine learning techniques used to support marketing decisions.
By the end of the semester, students should be able to transform marketing data into meaningful insights, identify customer behaviour patterns, evaluate marketing performance and apply introductory predictive models to real-world marketing problems.
3. Detailed Semester Programme
The following programme is organised into 12 teaching sessions, progressing from fundamental concepts to practical marketing applications.
Session 1: Introduction to Marketing Data Analysis and Machine Learning
Key concepts, objectives and applications
-
Definition and importance of marketing data analysis.
-
Types of marketing data: quantitative and qualitative.
-
Introduction to artificial intelligence, machine learning and predictive analytics.
-
Applications in customer relationship management, digital marketing and market research.
Practical application: Identify the types of data collected by an online retailer.
Session 2: Data Collection, Types and Sources
Understanding marketing datasets
-
Primary and secondary data.
-
Internal and external data sources.
-
Customer databases, surveys, social media and website analytics.
-
Variables, observations and data structures.
Practical application: Build a customer dataset containing age, purchase frequency, spending and satisfaction.
Session 3: Data Cleaning and Preparation
Preparing data for analysis
-
Identifying missing values and duplicates.
-
Detecting errors and outliers.
-
Coding categorical variables.
-
Data transformation, normalisation and standardisation.
-
Introduction to data preparation using Excel or Python.
Practical application: Clean a customer database before analysing purchasing behaviour.
Session 4: Descriptive Statistics for Marketing
Summarising and interpreting data
-
Mean, median, mode and standard deviation.
-
Frequencies, percentages and distributions.
-
Cross-tabulation and comparison of customer groups.
-
Tables, charts and dashboards.
Practical application: Analyse average customer spending and satisfaction levels.
Session 5: Correlation and Regression Analysis
Explaining relationships between variables
-
Pearson's correlation coefficient.
-
Simple and multiple linear regression.
-
Dependent and independent variables.
-
Interpretation of coefficients and \(R^2\).
-
Correlation versus causation.
Practical application: Examine the relationship between advertising expenditure and sales revenue.
Session 6: Fundamentals of Machine Learning
Concepts, methods and learning processes
-
Definition and principles of machine learning.
-
Supervised and unsupervised learning.
-
Classification and regression.
-
Training data, testing data and model learning.
-
Introduction to algorithms and model selection.
Practical application: Distinguish between classification, regression and clustering problems in marketing.
Session 7: Customer Segmentation and Clustering
Understanding customer groups
-
Principles of market segmentation using data.
-
Introduction to the K-means algorithm.
-
Selecting relevant customer characteristics.
-
Interpreting clusters and developing marketing strategies.
Practical application: Segment customers according to spending, purchase frequency and recency.
Session 8: Classification Models in Marketing
Predicting customer decisions
-
Introduction to logistic regression and decision trees.
-
Customer response and purchase prediction.
-
Customer churn prediction.
-
Classification results and confusion matrices.
Practical application: Predict whether a customer is likely to respond to a promotional campaign.
Session 9: Predictive Analytics and Sales Forecasting
Anticipating future market outcomes
-
Introduction to predictive analytics.
-
Sales forecasting and demand estimation.
-
Trend analysis and time-series fundamentals.
-
Forecast interpretation and business implications.
Practical application: Forecast monthly sales using historical data and a simple forecasting method.
Session 10: Model Evaluation and Performance Metrics
Measuring predictive accuracy
-
Training and testing sets.
-
Overfitting and underfitting.
-
Classification metrics: accuracy, precision, recall and F1-score.
-
Regression metrics: MAE, MSE and RMSE.
-
Choosing a model according to the marketing objective.
Practical application: Compare two customer response prediction models and select the more suitable one.
Session 11: Marketing Campaign Analytics and KPIs
Measuring marketing performance with data
-
Key performance indicators (KPIs).
-
Click-through rate (CTR), conversion rate (CVR) and cost per lead (CPL).
-
Return on advertising spend (ROAS) and return on investment (ROI).
-
Campaign comparison and customer acquisition analysis.
-
Using analytical insights to optimise marketing budgets.
Practical application: Calculate campaign KPIs, compare campaign results and recommend improvements.
Session 12: Marketing Analytics Ethics, Privacy and Final Case Study
Responsible and practical use of data
-
Customer privacy and data protection.
-
Informed consent and responsible data collection.
-
Algorithmic bias and fairness.
-
Responsible use of artificial intelligence.
-
Integrated marketing data analysis project.
Practical application: Analyse a marketing case study, interpret the results and propose data-driven recommendations while respecting customer privacy.
- المعلم: M Bouhafs