Areeb Sajid
Data Analyst | Researcher | Musician | Equestrian
Hold the cursor on a node for three seconds to jump to that section, or click it to go straight away. Drag to rotate.
The best thing about being a statistician is that you get to play in everyone's backyard.
About
Statisticians look hardest at what a model can’t explain. Most of my work can be explained by a few variables: I turn messy data into decisions people can defend, and I distrust any answer I can’t justify. The residuals are where it gets interesting. A bass line at the back of a stage taught me to hold the rhythm so others sound better. A horse that reads your mood taught me calm and consistency. A ridge where the weather decides the plan taught me to prepare thoroughly and adapt quickly. I keep all of it in the model, and I’m looking for a programme that will stress-test it.
Education
Bachelor of Sciences in Statistics
Publications
CRAVE: Climate Risk Attribution and Vulnerability Evaluation via Explainable Machine Learning
Sajid Areeb and Jamaluddin CRAVE: Climate Risk Attribution and Vulnerability Evaluation via Explainable Machine Learning.
BEaCON: Benchmarking Ensemble and Classical Models for Blockchain Fraud Detection
Sajid Areeb, Khan Yusufi Faiz Noor and Jamaluddin BEaCON: Benchmarking Ensemble and Classical Models for Ethereum Fraud Detection.
Gender Bias in End-to-End Speech Translation: A Review
A structured review of 50 studies on gender and other biases in speech translation and language systems, with verified data extraction and a visual synthesis of the evidence.
Internships
Data Analyst Intern
Data Analyst Intern
Data Analyst Intern
Conferences, workshops and summer schools
Data Science Summer School (DS³)
Climate and Energy Policy for Early Researchers
International Conference on the Educational and Economic Status of Muslims in India (CEPECAMI)
Xth International Symposium on Statistics, Optimization, and Related Fields
Technical Ethical Hacking Workshop
Online courses
Introduction to the Internet of Things (IoT)
Projects
Air quality analysis for Aligarh
Studies daily AQI patterns and compares consumer-app readings against official CPCB data availability, with attention to data provenance.
Minority representation in official Indian datasets
Audits ten domains of official statistics to show how category design shapes what the data can and cannot say, using an epistemic-injustice framework.
Netflix content trends analysis
Analysed more than 8,000 titles to uncover trends by genre, country and content type, and used them to suggest content for different regions.
Airbnb price prediction
Built and evaluated regression models for listing prices from listing and review features, comparing their performance with RMSE and R².
Awards and grants
Travel Grant
Co-curricular activities
Music Society Coordinator
Guitarist and Bassist
Equestrian (Horse Riding) and Mountaineering
Research interests
Statistical Modelling · Optimization · Geostatistics
Contact
Hypothesis: we should talk.
The null says nothing happens. I’m betting on the alternative: a collaboration, a supervision conversation, an opportunity, or a problem your model can’t explain. Tell me what you’re working on and help me reject the null.