Here is the full detailed PPT prompt — slide by slide, ready to hand off to any tool (PowerPoint, Google Slides, Canva, or an AI design tool): --- ## PPT Prompt: AI/ML-Based Student Performance & Attendance Analytics **20 slides | 10 minutes | Internship Presentation** --- ### **SLIDE 1 — Title Slide** **Visual:** Dark navy blue background, subtle abstract data-node/network pattern on the right half. Clean and professional. **Content:** - Big bold title: **"AI/ML-Based Student Performance & Attendance Analytics"** - Subtitle: *"Early Risk Identification for College Administration"* - Name: Shivansh Chaturvedi | Enrollment: 2401200009 - B.Tech (Mathematics and Computing), JIIT Noida - Internship at CMIT, Sidhi | May–July 2026 - Supervisor: Dr. Manoj Mishra --- ### **SLIDE 2 — The Hook (Why This Matters)** **Visual:** A single powerful statistic on the left. On the right, a simple illustration: a student at a desk, clock ticking, red warning symbol. **Headline:** *"Faculty find out a student is failing — only after it's too late."* **3 bullet points (large font, short):** - Attendance logs exist. Marks exist. Backlogs exist. - None of it is connected to a warning system. - By semester end, intervention is too late. **Bottom line:** *"This project asks: can we catch the problem early?"* --- ### **SLIDE 3 — Where I Interned** **Visual:** Simple two-column layout. Left: icon of a building. Right: a small India map pin on Madhya Pradesh. **Headline:** *"Host Organization — CMIT, Sidhi"* **Content (table-style, clean rows):** - Organization: Centre for Management & IT (CMIT), Sidhi - Affiliated with: Makhanlal Chaturvedi National University, Bhopal - Domain: Data Science & AI Training - Supervisor: Dr. Manoj Mishra, Principal - Duration: 28 May 2026 — 09 July 2026 (6 weeks) **One-liner at bottom:** *"Project-based training — no isolated exercises, one full real-world problem."* --- ### **SLIDE 4 — The Problem Statement** **Visual:** Red-tinted slide with a bold quote block in the center. **Headline:** *"What problem are we actually solving?"* **Center quote (large, styled):** > *"Faculty and academic administrators lack a simple, data-backed way to identify at-risk students during the semester — not after it ends."* **Below the quote, 3 pain points in boxes:** - 📂 Data is siloed — attendance in one system, marks in another - 👁️ Reviews are manual, department by department - ⏰ Flagging happens after results — too late to act --- ### **SLIDE 5 — Objectives** **Visual:** Clean white/light card layout. 5 cards with icons. **Headline:** *"What I set out to do"* **5 objective cards:** 1. 🔄 Experience the complete Data Science lifecycle end-to-end 2. 🤖 Apply supervised ML to a structured student dataset 3. 🔍 Identify the strongest predictors of academic risk 4. 🏷️ Build a classifier that flags at-risk students reliably 5. 📣 Present findings in a way non-technical staff can act on --- ### **SLIDE 6 — The Pipeline (Big Picture)** **Visual:**