Highlights
- Distinguish between Predictive AI and Generative AI.
- Turn business questions into Machine Learning tasks for data-driven decisions.
- Use Python (Pandas, Matplotlib, Seaborn) to explore and visualise data from various sources.
- Train a Machine Learning Classifier with Scikit-Learn (Decision Trees, Logistic Regression, Neural Networks).
- Segment customer markets with K-Means and Hierarchical algorithms.
- Uncover hidden customer behaviours with Association Rules and build a Recommendation Engine.
- Analyse relationships using Social Network Analysis.
- Create predictive models (e.g. revenue) with Linear Regression.
- Test your skills with the end-of-course exam.
- Access continued support with one-on-one instructor coaching and computing sandbox.
Course Details
Module 1: The Role of a Data Scientist
- Key skills required for a Data Scientist.
- Combining technical and non-technical roles.
- Differences between Data Scientists and Data Engineers.
- The full lifecycle of Data Science within an organisation.
- Translating business questions into AI/ML models.
- Exploring diverse data sources for business insights.
- Generative AI vs. Discriminative AI.
Module 2: Data Manipulation and Visualisation with Python
- Key Python features for Data Scientists.
- Using Pandas to view and manipulate data.
- Importing/exporting data (Databases, Google Images, etc.).
- Selecting, filtering, and applying functions with Pandas.
- Handling duplicates, missing values, and data normalisation.
- Visualising data with Pandas, Matplotlib, and Seaborn.
Module 3: Preprocessing Unstructured Data with NLP
- Preprocessing unstructured data (web ads, emails, blogs).
- Common NLP techniques: stemming and stop words.
- Creating term-document matrices for analysis.
- Integrating Large Language Models (LLMs).
Module 4: Linear Regression and Feature Engineering
- Solving business problems with linear regression (e.g., revenue prediction).
- Identifying predictors for target variables.
- Evaluating regression models using RMSE.
- Using feature engineering to improve models.
Module 5: Classification Models and Evaluation
- Building and using AI/ML classifiers (e.g., Customer Churn).
- Training, testing, and validating classification models.
- Evaluating decision tree classifier performance.
Module 6: Alternative Classification Approaches
- Exploring alternative classification methods.
- Understanding the role of activation functions in Logistic Regression.
- Using Neural Networks and Deep Learning (e.g., self-driving cars).
- Probability foundations of Naive Bayes classifiers.
- Evaluating classification models (ROC, AUC, Precision, Recall, etc.).
Module 7: Clustering for Customer and Product Segmentation
- Segmenting customers/products with clustering algorithms.
- Implementing similarity measures in Python.
- Top-down clustering with K-Means.
- Bottom-up clustering with hierarchical algorithms.
- Clustering unstructured data (e.g., Tweets, Emails).
Module 8: Association Rules and Recommender Systems
- Modelling customer behaviour with Association Rules.
- Evaluating models using support, confidence, and lift.
- Feature engineering to enhance models.
- Building custom recommender systems.
Module 9: Network Analysis for Insights
- Analysing organisational relationships through network analysis.
- Visualising connections to uncover business insights.
- Ego-centric vs. socio-centric analysis.
Module 10: Big Data Analytics, Communication, and Ethics
- Cloud-based Big Data analytics (Microsoft, Amazon, Google).
- Communicating and handling ethics in Data Science.
- Discussing AI ethics and future implications.
- Exploring continuous learning paths for Data Scientists.
Who should attend
This course is ideal for aspiring Data Scientists, analysts, or anyone interested in gaining practical skills in AI and Machine Learning using Python.
It’s suitable for professionals in business, finance, marketing, or tech who want to harness data for decision-making and build predictive models. A basic understanding of Python is recommended, but no prior AI or ML experience is necessary.
Feedback
4.8 out of 5 average
"The course was professionally run and I liked that it is interactive with exercises of how AI is used. The instructor is very knowledgeable on the subject and enthusiastic about machine learning" YZ, Software developer, Python AI & ML, May 2022
