This interdisciplinary program focuses on the analysis and handling of data from multiple sources and for various applications in order to draw inferences from it, combining topics from mathematics, statistics, and computer science. These topics include probability theory, inference, least-square estimation, maximum likelihood estimation, finding local and global optimal solutions (gradient descent, genetic algorithms, etc.), and generalized additive models. It also covers machine learning topics such as classification, conditional probability estimation, clustering, and dimensionality reduction (e.g. discriminant factor and principal component analyses), and decision support systems. The program also covers big data analysis, including big data collection, preparation, preprocessing, warehousing, interactive visualization, analysis, scrubbing, mining, management, modeling, and tools such as Hadoop, Map-Reduce, Apache Spark, etc.

 Degree Plan

Courses Descriptions:

MATH 405: Learning from Data                                                                                            (3-0-3)

Description: Review of Basic vector and matrix operations, Factorizations, Basic Probability Theory,  Inference, Least-Square Estimation, Maximum Likelihood Estimation, Gradient Descent.  Applications to Machine Learning using Linear Regression and Neural Networks. 

Prerequisite: MATH 102 and (STAT 201 or STAT 319 or ISE 205), and ICS 104 

 STAT 413: Statistical Modeling                                                                                         (3-0-3)

Description: Simple and Multiple Linear Regression, Polynomial Regression, Splines; Generalized Additive Models; Hierarchical and Mixed Effects Models; Bayesian Modeling; Logistic Regression, Generalized Linear Models, Discriminant Analysis; Model Selection.

Prerequisite:  MATH 405

 

ICS 474: Big Data Analytics                                                                                          (3-0-3)

Description: Introduction and foundation of big data and big-data analytics. Sources of big data. Smart clouds. Hadoop file system and Apache Spark. Storage management for big data. Machine learning and visualization with big data. Applications of big data. Big data security, privacy, and its societal impacts.

Prerequisite: (MATH 101 or MATH 106), (ISE 205 or STAT 201 or STAT 212 or STAT  319 or EE 315)

 

ISE 487: Predictive Analytics Techniques                                                                            (3-0-3)

Description: Characteristics of time series, trends, seasonality, noise, stationarity; Statistical background and model evaluation methods; Time series regression, variable selection and general linear regression; Exponential Smoothing and seasonal data; ARIMA based models including MA, AR, ARMA, ARIMA and SARIMA, Model validation and parameter estimation; Advance predictive analytics: Multivariate prediction, state space models, neural networks, spectral analysis and Bayesian methods.

Prerequisites: (MATH 405 OR ISE 315), (ICS 102 OR ICS 103 OR ICS 104)

Eligibility for Admission

• Minimum GPA of 2.0 is required for all BSc KFUPM students.
• Students with applied major cannot enroll in concentrations.
• Students with 79 – 115 hours completed.
• KFUPM students enrolled in BS degree program who completed junior  level courses in Sciences or Engineering are eligible to apply.