Last updated 05.05.2026

About Me

Hi, I am Akanksha, an aspiring researcher. With a background in Computational Social Science, I am very passionate about electoral forecasting (in India more than other countries for now). I am currently working at CERN modelling a twin of a part of the Future Circular Collider.

Experience

My past experience, including both industry and research.

Machine Learning Engineer @CERN

September 2025 - Present

Using deep-learning and simulations to model a digital twin of a component of the Future Circular Collider. Previously designed:View them here.

Research Assistant

November 2023 - Present

Exploring how multilevel regression and post-stratification and LLMs can reduce selection bias in unrepresentative survey data with Dr. Roberto Cerina.

Collaborated with Dr. Rens Wilderom on multiple cultural sociology projects where I conducted web-scraping, media processing, network analysis and some NLP.

Projects

Some projects I worked on.

Manifesto & Vote-share Prediction Model

University of Amsterdam, 2024

Developed a model to learn relation between vote-share and manifesto standpoints. Audited the model & used SMOTE to tackle underrepresentation.

Inclusive Website for Dutch Police

2023

Built a web-app with and for the Dutch National Police to optimise officer deployment.

Matching Algorithm for Healthcare Professionals

Sigra, 2023

Designed a matching algorithm to connect Dutch healthcare-workers with organisations based on skills and interests.

Blogs

Long-form reflections, research notes, and thought pieces.

Can an AI Predict Who West Bengal Will Vote For?

We simulated 20,000 voters with an LLM and asked each one to reason through their own decision and provide a vote choice for the 2026 West Bengal elections

Data Visualization on Internet Freedom

Created a visualisation platform showing global internet freedom trends and electoral integrity using advanced data analysis.

The Future of Humanity and AI

As remote as it may sound, the notion that machines could have higher intelligence than humans and exert control over us is a possibility. The big question is whether these machines will use their power to become a threat.

Agentic AI and Agency

We are facing a new reality. Machines are not becoming people but are becoming actors in systems that impact us. To respond, we need to rethink some key philosophical concepts. Agency is one such concept that is no longer just a human trait but extends to technology.