AI for Research and Data Analysis

Instructor: Istiaq Ahmed Fahad

Term: July 2026

Location: Institute of Information Technology (IIT), University of Dhaka

Course Overview

A practical program helping non-technical students build confidence in AI and data analytics for academic research. Through guided, hands-on practice, participants learn to collect, clean, analyze and interpret data, with new coverage of AI ethics, statistical thinking, prompt engineering and AI-powered research tools, culminating in an end-to-end mini-project.

Prerequisites

Familiar with Python and Statistics.

Schedule

Topic	Materials
Class 1 — Introduction to AI & Data Analysis AI in research, data types and role of AI in modern research.
Class 2 — Exploring Research Use Cases Domain-specific examples and understanding research problems.
Class 3 — Data Collection Basics Survey data, open datasets, formats and ethical collection.
Class 4 — Introduction to Google Colab, AI Models & Responsible Use Colab notebooks, importing data, what AI models are, responsible and ethical AI use.
Class 5 — Data Cleaning I Missing values, duplicates and formatting issues.
Class 6 — Data Cleaning II Transformation, feature selection and automation.
Class 7 — Exploratory Data Analysis I Descriptive statistics and visualizing distributions.
Class 8 — Exploratory Data Analysis II Correlation, relationships and chart types.
Class 9 — Exploratory Data Analysis III Advanced visualizations and AI-assisted insights.
Class 10 — Prompt Engineering for Research & Data Analysis Strong vs weak prompts, role prompting, chain-of-thought, few-shot and research prompting.
Class 11 — Introduction to Applied AI Classification, regression, clustering and AI workflow.
Class 12 — Applying AI to Text Data Summarization, keyword extraction, sentiment and classification.
Class 13 — Applying AI to Structured Data Regression, classification and clustering.
Class 14 — Interpreting Model Outputs Accuracy, errors, visual interpretation and insights.
Class 15 — Reporting Results Tables, charts, narratives and visual storytelling.
Class 16 — AI Tools for Literature Review & Research Writing NotebookLM, Elicit, Consensus, Perplexity and their limits.
Class 17 — Mini-Project Setup Dataset selection and research question planning.
Class 18 — Mini-Project Analysis I Cleaning, EDA and initial AI applications.
Class 19 — Mini-Project Analysis II Model application, visualization and report refinement.
Class 20 — Mini-Project Presentation Final insights, presentation and feedback.