DATA-463-christina.myers-2026-09-28-10-55-51

Machine Learning in Data & AI

DATA 463

Semester and Year [tbd]

3 Credit Hours

Prerequisites: DATA 302, DATA 219, and STAT/DATA 360

Course Details

Day and Time: [tbd]

Meeting Location: [tbd]

Instructor Contact Information

Instructor Name: [tbd]

Instructor Contact Information: [office location, phone, email] [tbd]

Instructor Office Hours: [click here for best practices] [tbd]

Course Overview

This course explores how machine learning transforms data into predictions, patterns, insights, and intelligent solutions for real-world analytical problems. Students develop a practical understanding of the machine learning process, from framing data-driven questions and preparing data to building, evaluating, comparing, and interpreting models. The course progresses from foundational supervised and unsupervised learning approaches to ensemble methods, recommendation systems, neural networks, and deep learning, examining how these methods can be applied to increasingly complex forms of data, including images, time-series, and text. Students also explore representation learning, generative models, and contemporary generative AI and large language models, connecting these advances to emerging applications in data analytics. Throughout the course, emphasis is placed on selecting appropriate methods for the data and analytical objective while considering model capabilities and limitations, explainability, fairness, privacy, robustness, and responsible use.

Course Materials

Books: None

Fees: None

Student Learning Outcomes (SLOs)

By the end of the course, students will be able to:

Formulate real-world data analytics problems as machine learning tasks by defining analytical objectives, identifying relevant data and target outcomes, and selecting appropriate learning approaches.
Prepare and transform data for machine learning using appropriate exploratory analysis, preprocessing, feature engineering, and dimensionality-reduction techniques.
Implement and apply machine learning methods for predictive and pattern-based analytics, including regression and classification, clustering, decision trees, and ensemble methods (e.g., random forests).
Evaluate, tune, compare, and select machine learning models using appropriate performance metrics, validation strategies, and model-selection techniques.
Explain the foundations and evolution of neural networks and deep learning, and apply these approaches to complex data, including feed-forward neural networks, CNNs, and recurrent architectures for image/spatial and time-series/sequential applications.
Explain and apply contemporary AI approaches to data analytics, including recommendation systems, generative models, transformers, and large language models.
Interpret and critically evaluate machine learning and AI results with consideration of explainability, fairness, robustness, privacy, limitations, responsible use, and human oversight.
Develop and communicate an end-to-end machine learning and AI solution to a real-world data analytics problem.

**Course Schedule**

**[Please note that a WSU semester is 15 weeks + Thanksgiving/Spring Break. The schedule below does not include the break.]**
Week	Broader Topic	Key Topics
Module 1: Foundations and Core Machine Learning (Weeks 1- 4)
Week 1 [dates]	Foundations of Machine Learning & AI	Role of ML in data analytics and AI; AI vs. ML vs. deep learning; foundations and evolution of AI; traditional programming vs. ML; supervised, unsupervised, and reinforcement learning; basic ML concepts and terminology; descriptive, predictive, and prescriptive analytics; overview of the ML analytics lifecycle; real-world applications.
Week 2 [dates]	Framing Problems for Machine Learning	Translating business and research questions into well-defined machine learning problems; identifying analytical objectives; defining inputs and target outcomes; determining appropriate ML problem types such as regression, classification, and clustering.
Week 3 [dates]	Data Preparation & Exploration for Machine Learning	Data sources and data types; data quality and representativeness; handling missing values and data-quality outliers; exploratory data analysis; feature-target relationships; encoding categorical variables; scaling and normalization; feature construction and selection; preprocessing pipelines; data leakage; responsible data use.
Week 4 [dates]	Unsupervised Learning & Pattern Discovery	Learning from unlabeled data; clustering and pattern discovery; k-means and hierarchical clustering; density-based clustering (DBSCAN); Self-Organizing Maps (SOM); evaluation and interpretation of unsupervised learning results; dimensionality reduction with PCA; nonlinear dimensionality reduction and visualization with t-SNE/UMAP; anomaly detection and Isolation Forest; applications of unsupervised learning in data analytics.
Module 2: Predictive Machine Learning & Model Development (Weeks 5-8)
Week 5 [dates]	Supervised Learning for Predictive Analytics	Supervised learning framework; regression vs classification; continuous vs categorical target variables; linear and logistic regression; regularization concepts; k-nearest neighbors (k-NN); Naive Bayes; support vector methods for regression and classification (SVR/SVM); regression and classification evaluation metrics; prediction and interpretation; implementation and comparison of supervised learning models.
Week 6 [dates]	Tree-Based & Ensemble Learning	Decision trees for regression and classification; splitting criteria and tree construction; Gini/entropy intuition; tree depth and pruning; bagging and random forests; boosting and gradient boosting; modern gradient-boosting methods such as XGBoost, LightGBM, and CatBoost; feature importance; implementation and comparison of tree-based and ensemble models; strengths and limitations of ensemble approaches.
Week 7 [dates]	Model Validation & Selection	Training, validation, and test sets; cross-validation strategies including k-fold and stratified cross-validation; underfitting and overfitting; bias-variance tradeoff; learning and validation curves; parameters vs hyperparameters; hyperparameter tuning; grid search, random search, and Bayesian optimization concepts; model comparison and selection based on analytical objectives.
Week 8 [dates]	Recommendation Systems	Recommendation and personalization problems; user-item interactions; content-based and collaborative filtering; user-based and item-based approaches; similarity measures; matrix factorization and latent representations; explicit vs implicit feedback; hybrid recommendation approaches; cold-start problem; recommendation evaluation; introduction to embedding-based and neural recommendation systems; applications and limitations.
Module 3: Neural Networks & Deep Learning (Weeks 9-13)
Week 9 [dates]	Artificial Neural Networks	Evolution of artificial neural networks and early neural models (e.g., McCulloch-Pitts neuron, Hebbian learning, perceptron, and ADALINE); multilayer perceptrons and feed-forward neural network architecture; input, hidden, and output layers; weights and biases; activation functions; forward propagation and loss functions; gradient descent and learning rate; backpropagation and weight updates; epochs, batches, and mini-batch training; regularization and dropout; training and evaluating a basic feed-forward neural network; Deep Belief Networks (DBNs) as an early deep-learning approach.
Week 10 [dates]	Deep Learning for Image & Spatial Data	Image and spatial data characteristics; convolutional neural network (CNN) architecture; convolution and filters; feature maps; pooling; learned feature representations; image classification; pretrained networks and transfer learning; implementation and applications of CNNs; limitations of image-based deep learning.
Week 11 [dates]	Representation Learning & Generative Models	Representation learning; autoencoders; encoder-decoder architecture; latent representations; variational autoencoder (VAE) concepts; generative modeling; GAN architecture and adversarial learning; synthetic data generation; introduction to diffusion models; applications and limitations of generative models.
Week 12 [dates]	Learning from Time-Series & Sequential Data	Temporal and sequential data; temporal dependence, trend, and seasonality; lagged features; forecasting problems; temporal training and validation strategies; RNN architecture and hidden states; LSTM and GRU concepts; sequence prediction and time-series anomaly detection; forecasting evaluation; introduction to attention-based approaches for sequential data; traditional vs. ML/deep-learning approaches.
Week 13 [dates]	Learning from Text & Language Data	Unstructured text data; text preprocessing and tokenization; traditional text representations such as bag-of-words and TF-IDF; embeddings and learned representations; attention and transformer architecture; pretrained language models; text classification and other data analytics applications.
Module 4: Contemporary & Responsible AI (Weeks 14-16)
Week 14 [dates]	Generative AI & Large Language Models	Generative AI concepts; generative language models and large language models (LLMs); prompting and in-context learning; retrieval-augmented generation (RAG); adaptation and fine-tuning concepts; generative AI applications in data analytics; capabilities and limitations of generative AI.
Week 15 [dates]	Responsible & Explainable Machine Learning	Model interpretability and explainability; global vs. local explanations; feature importance; SHAP/LIME concepts; bias and fairness; robustness; distribution and concept drift; privacy risks in machine learning and generative AI; privacy-preserving machine learning concepts; responsible use of predictive and generative models; limitations of ML and AI systems; human oversight.
Week 16	Final Week	Final project completion/presentation.

Expectations for Student Effort

Students are expected to spend a minimum of 9 hours per week on a three-credit course, of which 3 hours are spent on instructor-led activities (lectures and discussions) and 6 hours are spent on outside activities. These outside activities include, but are not limited to reading, studying, problem solving, writing, homework, and other preparations for the course. Achievement of course goals may require more than the minimum time commitment. For the most accurate and up to date information go to Academic Regulations.

Grading

**Assignments and Projects**
Type of Assignment (tests, papers, etc)	Percent of Overall Grade
Weekly Assignments	50%
Midterm Exam	20%
Final Project	30%

Grading Schema
Grade	Percent	Grade	Percent
A	93-100	C	73-76.99
A-	90-92.99	C-	70-72.99
B+	87-89.99	D+	66-69.99
B	83-86.99	D	60-65.99
B-	80-82.99	F	0-59.99
C+	77-79.99

Attendance and Make-Up Policy

Students should make all reasonable efforts to attend all class meetings. However, in the event a student is unable to attend a class, it is the responsibility of the student to inform the instructor as soon as possible, explain the reason for the absence (and provide documentation, if appropriate), and make up class work missed within a reasonable amount of time, if allowed. Missing class meetings may result in reducing the overall grade in the class.

Academic Integrity Statement

You are responsible for reading WSU's Academic Integrity Policy, which is based on Washington State law. If you cheat in your work in this class you will:

-Be reported to the Center for Community Standards

-Have the right to appeal my decision

-Not be able to drop the course of withdraw from the course until the appeals process is finished

If you have any questions about what you can and cannot do in this course, ask me.

If you want to ask for a change in my decision about academic integrity, use the form at the Center for Community Standards website. You must submit this request within 21 calendar days of the decision.