Miguel Rivera-Lanas

Data Scientist / Engineer



AI/ML directed automated systems are increasingly embedded in, reflective of, and consequential to the operation of social and political systems.

On the one hand, this trend broadens the methods researchers can use to understand social trends with better granularity, high frequency, at at lower cost. On the other, researchers should be actively investigating the feedback loops between social and technical systems that, left unchecked, have been demonstrated to systematically produce negative and inequitable social outcomes.

The aspects of these topics I pursue in this blog relate to NLP, political disinformation, and socio technical systems generally.


  • Measuring AI/ML Fairness and Bias
  • Statistics / Probabilistic Modeling
  • Computational Sociology
  • Political Extremism, Propogation of Disinformation


  • BA Economics, Minor(s)- Statistics, International Relations, 2017

    University of Pennsylvania



Data Scientist / Engineer


Sep 2019 – Present New York, NY
  • Sept 2019 to Aug. 2020, I was part of a research and learning group, investigating use cases for using novel data sets, including credit-cardtransaction panel data, website traffic, cell-phone geolocation panels, and others for discovering trends related to fundamental KPIs for companies.
  • In Sept. 2020, I joined an investment team with eight sector analysts, where I manage all data science and engineering projects.
  • Implement statistical descriptive modeling, preprocessing, feature engineering, and forecasting over a diverse range of data sets related to oil well production, retail consumer trends, and othe rsectors.
  • Analyze sector exposure to risk factors, inter-sector correlations, and build systematic strategy backtesting framework
  • Build scalable and robust cloud based event-driven ETL architecture fordelivering continuous reporting of data product

Research Associate; Fixed Income


Jul 2017 – Aug 2019 New York, NY
  • Rotations as research associate for macro economics, quantitative research, and portfolio strategy technology teams
  • Developed and maintained ETL, preprocessing, and reporting for novel liquidity signals from live order-book data, utilized by traders to better assess supply and demand conditions for specific parts of the market

Recent Course Posts

Scala Intro

================================ Lecture 6.1: Other Collections ================================ Other Sequences another Seq …

Scala Intro

================================ Lecture 5.1: More Functions on Lists ================================ Sublists and element access: …

Scala Intro

Lecture 4.1: Objects Everywhere: Pure Object Orientation in which every value is an object if lang is based on classes, this means …

Recent Posts

Sociotechnical Systems in Fairness & Accountability Research

In contemporary discussions about fairness and accountability regarding the mass implementation of ML systems and participatory …

Spark Internals

These notes are based on the following lectures: Spark Core and Internals 2015 by Sameer Farooqui deeper understanding by Daniel Tomes …

538 Riddler: Robopizza

This Riddler puzzle is about cutting a circle at random points and understanding how many slices are likely to result. “At …