Billel Arbaoui (Aj. Bill)

Information and communication technology (ICT) Department

ICT 338 - Intelligent Systems

​

Introduction and Select a Business Case

ICT 338 - Intelligent Systems

​

Week 1: Introduction & AI for Customer Behavior

Week 2: Rule-Based Systems & Fuzzy Logic

Week 3: Case-Based Reasoning for Customer Behavior & Ethics

Week 4: Agent-Based Modeling and Simulation (ABMS) – Part 1

Week 5: Agent-Based Modeling and Simulation (ABMS) – Part 2

Week 6: Deep Learning with ABMS – Part 1

Week 7: Deep Learning with ABMS – Part 2

Week 9: Midterm & Flask API Intro

Week 10: Building Flask APIs for Customers – Part 1

Week 11: Building Flask APIs for Customers – Part 2

Week 12: Flask APIs for Customer Dashboards

Week 13: Flask APIs for Customer IoT

Week 14: Flask APIs for Customer Automation

Week 15: Final Project Presentations

15-week course on

Intelligent Systems

​

​

• Master AI fundamentals (intelligent agents, fuzzy logic, neural networks, evolutionary computation) for customer behavior analysis.

​

​

Course Goals

​

​

• Master AI fundamentals (intelligent agents, fuzzy logic, neural networks, evolutionary computation) for customer behavior analysis.

​

• Design and deploy hybrid intelligent systems

(CBR + ABMS) as Flask APIs on Firebase.

​

• Explore real-world applications (e.g., retail, IoT)

with ethical responsibility.

Course Goals

• Required Software: Python (3.8+), Mesa (ABMS), Flask, Streamlit, Firebase.

​

• Textbooks: “Artificial Intelligence” by Negnevitsky; “Agent-Based Modeling” by Railsback & Grimm.

​

• Online Resources: Flask, Streamlit, Firebase documentation.

​

• Prerequisites: Basic Python, and business concepts (no prior AI experience needed).

​

• Access: Personal computer with internet, free Firebase/simulation accounts.

What is AI for Customer Behavior?

What is AI for Customer Behavior?

What is AI for Customer Behavior?

Key AI Concepts for Customer Behavior

• Intelligent Agents: Autonomous systems for customer tasks (e.g., chatbots for support).

​

Key AI Concepts for Customer Behavior

• Intelligent Agents: Autonomous systems for customer tasks (e.g., chatbots for support).
• Expert Systems: Rule-based decisions (e.g., “if low purchases, offer discount”).

​

Key AI Concepts for Customer Behavior

• Intelligent Agents: Autonomous systems for customer tasks (e.g., chatbots for support).
• Expert Systems: Rule-based decisions (e.g., “if low purchases, offer discount”).
• Fuzzy Logic: Handles uncertain preferences (e.g., “likely to buy”).

​

Key AI Concepts for Customer Behavior

• Intelligent Agents: Autonomous systems for customer tasks (e.g., chatbots for support).
• Expert Systems: Rule-based decisions (e.g., “if low purchases, offer discount”).
• Fuzzy Logic: Handles uncertain preferences (e.g., “likely to buy”).
• Neural Networks: Detect patterns in customer data (e.g., churn from purchase history).

​

Key AI Concepts for Customer Behavior

• Intelligent Agents: Autonomous systems for customer tasks (e.g., chatbots for support).
• Expert Systems: Rule-based decisions (e.g., “if low purchases, offer discount”).
• Fuzzy Logic: Handles uncertain preferences (e.g., “likely to buy”).
• Neural Networks: Detect patterns in customer data (e.g., churn from purchase history).
• Evolutionary Computation: Optimize strategies (e.g., best promotion).

​

Key AI Concepts for Customer Behavior

• Intelligent Agents: Autonomous systems for customer tasks (e.g., chatbots for support).
• Expert Systems: Rule-based decisions (e.g., “if low purchases, offer discount”).
• Fuzzy Logic: Handles uncertain preferences (e.g., “likely to buy”).
• Neural Networks: Detect patterns in customer data (e.g., churn from purchase history).
• Evolutionary Computation: Optimize strategies (e.g., best promotion).
• ABMS: Simulate customer interactions (e.g., retail store behavior) for deep learning.

Select a Business Case

Step 1: in teams of 4–5 students, choose a customer-centric business case for your final project

Select a Business Case

Step 2: understanding Behavioral & Mental Thinking Theories

Select a Business Case

Step 2: understanding Behavioral & Mental Thinking Theories

​

Prospect Theory

Select a Business Case

Step 2: understanding Behavioral & Mental Thinking Theories

​

Cognitive Dissonance Theory

Select a Business Case

Step 2: understanding Behavioral & Mental Thinking Theories

​

The Love Matrix

Select a Business Case

Step 3:

How do these theories explain behaviors (e.g., cart abandonment, loyalty)?

Which theory best fits your chosen business case?

​

Select a Business Case

Step 3:

How do these theories explain behaviors (e.g., cart abandonment, loyalty)?

Which theory best fits your chosen business case?

​

Coffee Shop Turnover with Disliked Brand and Program

• Quadrant: Low Brand Love, Low Program Love
• Problem: Customers dislike a new coffee chain and its rewards program due to inconsistent quality and low value.
• Theory Fit: TPB—Analyze how negative attitudes (poor quality) and weak norms (no peer endorsement) lead to churn.
• Team Task: Study why customers avoid the brand and its program.

Select a Business Case

Step 3:

How do these theories explain behaviors (e.g., cart abandonment, loyalty)?

Which theory best fits your chosen business case?

​

Online Gaming Community Loyalty with Active Membership Program

• Quadrant: High Brand Love, High Program Love
• Problem: Gamers love a gaming platform and its membership perks but reduce activity during updates.
• Theory Fit: Cognitive Dissonance—Investigate how love for the brand/program conflicts with frustration from updates, causing temporary disengagement.
• Team Task: Explore why activity drops despite high love for both.