Data Science Bootcamp
Here's what you'll learn:
Enroll in this learning track and begin your journey to improving your skills.
Exploratory Data Analysis
Covers techniques for summarizing, visualizing, and understanding a dataset before modeling, including handling missing values, outliers, and distributions.
Storytelling With Data
Focuses on turning analysis into clear, persuasive narratives for non-technical stakeholders using effective visualization and framing. Emphasizes choosing the right chart types and structuring insights so decisions actually get made.
Predictive Modeling for Real World Problems
Introduces the end-to-end workflow of building predictive models on messy, real-world data, from problem framing to deployment considerations. Bridges theory with the practical trade-offs data scientists face outside clean textbook datasets.
Decision Trees
Explains how tree-based models split data to make predictions, covering concepts like entropy, information gain, and overfitting control. A core building block for understanding more advanced ensemble methods later in the curriculum.
Evaluation of Classification Models
Teaches how to assess classifier performance using metrics like precision, recall, F1, ROC-AUC, and confusion matrices. Helps learners choose the right metric based on business context, such as imbalanced classes or cost-sensitive errors.
Regularization and Tuning of Linear Models
Covers techniques like Ridge, Lasso, and Elastic Net to prevent overfitting and improve generalization in linear models. Also addresses hyperparameter tuning strategies to squeeze out optimal model performance.
Ensemble Learning, Bagging & Random Forest
Explores how combining multiple weak learners improves predictive accuracy and stability, with Random Forest as the flagship bagging algorithm. Highlights how bagging reduces variance compared to single decision trees.
Boosting
Dives into sequential ensemble techniques like AdaBoost, Gradient Boosting, and XGBoost that iteratively correct prior errors. Known for producing some of the highest-performing models in structured/tabular data competitions.
Online Experimentation And A/B Testing
Covers the statistical foundations and practical design of controlled experiments to measure product or feature impact. Includes topics like sample size calculation, statistical significance, and common pitfalls that invalidate results.
Text Analytics Fundamentals
Introduces core NLP techniques such as tokenization, stemming, TF-IDF, and basic sentiment analysis for extracting insight from unstructured text. Sets the stage for more advanced natural language processing work.
Introduction to Agentic AI
Explore the evolution of Agentic AI, its capabilities, and its impact on real-world AI systems. Gain insights into building smarter, more autonomous language models.
Unsupervised Learning with K-means Clustering
Explains how to group similar data points without labeled outcomes, using distance metrics and centroid-based clustering. Covers practical considerations like choosing the number of clusters and evaluating cluster quality.
Linear Models for Regression
Establishes the fundamentals of linear regression, including assumptions, coefficient interpretation, and diagnostics for model fit. Serves as the statistical backbone for many more advanced modeling techniques.
Ranking and Recommendation Systems
Covers the algorithms behind personalized recommendations and search ranking, including collaborative filtering and content-based approaches. Addresses real-world challenges like cold-start problems and scalability.