You're pledging to donate if the project hits its minimum goal and gets approved. If not, your funds will be returned.
I'm an incoming PhD researcher in Statistics for Data Science at Universidad Carlos III de Madrid (UC3M). My research focuses on prediction markets, particularly whether platforms such as Polymarket provide reliable forecasts during political and geopolitical events.
Prediction markets are increasingly used to estimate the likelihood of elections, conflicts, and other important events. But how much can we trust their probabilities when trading is concentrated among a small number of participants, liquidity is limited, or prices are vulnerable to manipulation?
I want to investigate these questions using historical market data and make the findings publicly available.
The project has three main goals:
Measure market concentration: Study whether a small number of traders account for a disproportionate share of activity in political and geopolitical prediction markets.
Investigate forecasting reliability: Examine how liquidity, trading activity, and market concentration relate to forecast accuracy.
Identify potential manipulation risks: Explore whether unusual trading patterns and concentrated positions are associated with distorted market probabilities.
I have already collected substantial historical data, including market concentration measurements and historical order-book observations.
The next stage is to validate the datasets, conduct statistical analysis, compare results across different market conditions, and prepare a research paper.
I intend to share reproducible code, research methods, and findings wherever data licensing and privacy restrictions permit.
I am seeking funding to support the research expenses associated with this project.
Funding would help cover:
Historical market data access and acquisition
Computing resources for statistical analysis
Data storage and research infrastructure
Research dissemination and publication-related expenses
The minimum funding would support a limited analysis using existing data. Additional funding would allow me to expand coverage, improve data quality, and conduct more extensive robustness checks.
I am currently leading this research independently as part of my preparation for doctoral studies at UC3M.
I hold an MSc in Big Data Technologies and Machine Learning from the University of Westminster, London, and a Bachelor's degree in Computer Science.
My professional experience includes blockchain development, financial data engineering, and quantitative trading infrastructure.
In 2026, I published a paper in Finance Research Letters titled "Stablecoins, Not Bitcoin: On-Chain Evidence of Dollar Demand During Armed Conflicts."
This work investigated cryptocurrency market behaviour during geopolitical conflicts using empirical financial data.
I have also been developing research on prediction-market concentration and forecasting accuracy, including collecting and validating large historical datasets.
The largest risk is incomplete historical market data, particularly the availability of historical order-book observations.
Other challenges include distinguishing manipulation from legitimate informed trading and identifying reliable causal relationships between concentration and forecasting performance.
If the full research objectives cannot be achieved, I intend to publish the methodological findings, data coverage limitations, and descriptive analysis.
Even a negative or inconclusive result could help researchers understand what can and cannot be inferred from historical prediction-market data.
I have not raised any funding in the past 12 months. This project is currently self-funded, and I have not received any grants, donations, or institutional financial support.