ABDULHAMEED IDRIS ADEDAMOLA

🛡️ Building a Dual-Layer AI Engine for NAFDAC Drug Verification Combining Exact Database Lookups with Machine Learning Fraud Inference for Real-Time Pharmaceutical Anti-Counterfeiting. 1. System Architecture: The Dual-Layer Verification Flow Standard verification systems rely solely on exact string matching against government registries. However, counterfeiters frequently exploit this by using slight spelling variations or reusing authentic codes on fake packaging. To solve this, we built a Dual-Layer Verification Architecture : 🟢 Layer 1: Direct Registry Lookup (Deterministic) Performs an instant hash/normalized check against official NAFDAC records. If an exact match is found, it immediately confirms the item as AUTHENTIC (100% Confidence) without triggering AI compute overhead. 🟡 Layer 2: Machine Learning Inference Engine ...

Why & How We Generated Synthetic Counterfeit Data for AI Drug Verification 1. The "Why": Solving the Positive-Class Bias Problem When building an AI system to detect counterfeit pharmaceuticals, you face an immediate data challenge: official government registries (like the NAFDAC Greenbook) only record authentic, approved products. If you train a Machine Learning model exclusively on genuine drug records: The AI Learns Nothing About Fraud: It only sees "good" data, so it defaults to predicting that every drug is 100% authentic. Extreme Class Imbalance: Without negative samples (counterfeits), supervised classifiers like Random Forest cannot establish a decision boundary to separate genuine products from fraudulent ones. To teach an AI how to spot fake drugs, you must show it what fake drugs look like. Because there is no public "official database of counterfeit dr...

🕷️ Scraping NAFDAC Greenbook from A to Z: How I Extracted 8,600+ Official Records into CSV Author: Idris Abdulhamood  |  Category: Web Scraping, Data Engineering & Automation The NAFDAC Greenbook ( greenbook.nafdac.gov.ng ) is the official public portal for all approved drugs, medical devices, herbals, and biologics registered by the Nigerian government. For data analysts, researchers, or software engineers, having this database in a clean, structured .csv format opens up endless possibilities—from fraud detection systems to market research. However, getting this data off the website and into an Excel sheet wasn't as simple as running pandas.read_html() . Here is the complete journey of how I scraped the entire portal from A to Z—including the wall I hit, why fast scripts failed, and the solution that successfully captured all 8,608 official entries . 🛑 P...