Predictive analytics using Python Certification Program

Powered by KPMG

Program Overview

Predictive Analytics Using Python is designed to help participants develop the skills needed to analyze data and generate reliable predictions with Python. The course covers key areas such as data preprocessing, exploratory data analysis, and the application of machine learning algorithms. Learners will work on hands-on projects to apply concepts in real-world contexts. By the end of the program, participants will be confident in using Python libraries like Pandas, NumPy, and Scikit-learn to build, test, and evaluate predictive models.

Course Content

Preprocess and transform data effectively to prepare it for machine learning applications.

  • Data pre processing
  • Data Transformation, Data Reduction
  • Data Wrangling and Manipulation for Machine Learning
  • Feature Scaling
  • Categorical Conversions

Learn and apply various regression techniques to analyze data trends and build accurate predictive models

  • Introduction to Machine Learning
  • Simple Linear Regression
  • Multiple Linear Regression
  • Support Vector Regressor
  • Decision Tree Regressor
  • Ridge and Lasso Regression

Understand key model validation techniques such as hold-out, cross-validation, and bootstrapping to assess model performance effectively.

  • Hold-out method
  • Cross Validation Method
  • Boot Straping method

Explore key classification techniques such as logistic regression, decision trees, and support vector machines (SVM) to build accurate predictive models.

  • Introduction to Classification Techniques
  • Logistic Regression
  • Ensemble techniques
  • Decision trees
  • Random Forest 
  • Naïve Bayes 
  • K-Nearest Neighbours
  • SMOTE 
  • Support Vector Machine 

Use evaluation metrics such as confusion matrix, accuracy, precision, recall, and F1-score to assess and compare model performance effectively.

  • Confusion Matrix
  • Accuracy
  • F1-Score, Precision, Recall 

Learn and apply clustering techniques such as hierarchical clustering, K-means, and DBSCAN to identify patterns and group similar data effectively.

  • Introduction to Unsupervised Learning
  • Heirarchial Clustering
  • K-Means Clustering
  • DBSCAN (Density Based Spatial Clustering of Applications with Noise)

Apply dimensionality reduction techniques such as PCA, SVD, and t-SNE to simplify data while preserving key patterns and insights.

  • Principal Component Analysis (PCA)
  • Singular Value Decomposition (SVD)
  • T-distributed Stochastic Neighbor Embedding (t-SNE)

Understand the principles of association rules and learn to build recommender systems that provide personalized suggestions based on user behavior.

  • Association Rule, FP Growth
  • Case Study
  • Apriori Algorith in Python
  • Recommender Systems
  • Weighted Score Recommender System
  • User Based Similarity

Tools & Platforms Learned

Global Certification by KPMG:

Business Analytics Professional Certification Program
skill labs
skill labs