CV [pdf]

Email: p[1st last name][2nd last name]@g.harvard.edu

---

About me

I am a second-year PhD student in computer science at Harvard University, advised by Prof. Milind Tambe. My research interests lie broadly at the intersection of artificial intelligence, social impact, and public policy. I am interested in the use of computational and mathematical methods to address global development challenges that can assist in the design of evidence-based public policies.

I hold a B.Sc. in Mathematics and a B.Sc. in Industrial Engineering from Universidad de Los Andes in Bogotá, Colombia. I was a Data Science for Social Good (DSSG) Fellow at The Alan Turing Institute in 2020 and a Student Undergraduate Research Fellow (SURF) at Cornell University in 2018. I Co-founded and currently co-organize the Centro de Analítica para Políticas Públicas (CAPP; Center of Analytics for Public Policy); a research initiative that aims to contribute and encourage research and development of mathematics, data science, and AI for the public sector in Colombia and Latin America. I also co-organizer the Machine Learning for the Developing World (ML4D) Workshop.

---

Research

Rigorously Reviewed Publications

• Fairness for Workers Who Pull the Arms: An Index Based Policyfor Allocation of Restless Bandit Tasks
  Biswas, A., Killian, J. A., Rodriguez-Diaz, P., Ghosh, S., and Tambe, M.
  AAMAS – International Conference on Autonomous Agents and Multiagent Systems, 2023.
  
• Flexible Budgets in Restless Bandits: A Proximal Primal-Dual Algorithm for Efficient Budget Allocation
  Rodriguez-Diaz, P., Killian, J. A., Xu, L., Suggala, A., Aparna, T., and Tambe, M.
  AAAI – Conference on Artificial Intelligence, 2023.
  * Oral presentation
  
• Robust Planning over Restless Groups: Engagement Interventions for a Large-Scale Maternal Telehealth Program
  Killian, J. A., *, Xu L.*, Biswas, A.*, Verma, S., Nair, V., Taneja, A., Hegde, A., Madhiwalla, N., Rodriguez-Diaz, P., Johnson-Yu, S., and Tambe, M.
  AAAI – Conference on Artificial Intelligence, 2023.
  * Oral presentation
  
• Understanding the Effect of Compliance with Quarantines and Lockdowns on Domestic Violence Occurrence in Bogotá
  Rodriguez-Diaz, P., Gomez, O., Garcia, J., Riascos, A., Moreno, J. S., Castro, J. D., and Panqueva, J. D.
  UNDP Latin America and the Caribbean, Working Papers Series, 2022.
  
• Visual Representations to Evaluate the Heterogeneous Effects of Urban Parks Restoration on Crime.
  Chitiva, J., Newball-Ramirez, D., Rodriguez-Diaz, P., Benavides, H., Dulce-Rubio, M., and Riascos, A.
  COMPASS – Conference on Computing and Sustainable Societies, 2021.
  
• Self-exciting point processes with image features as covariates for robbery modeling.
  Dulce-Rubio, M., Rodriguez-Diaz, P., Moreno, J., Riascos, A., and Camargo, J.
  Proceedings of the Computing Conference, 2021.
  
• Zero-Inflated Embeddings to Analyze Homicide Occurences Patterns.
  Benavides, H., Gomez O., Dulce-Rubio M., Rodriguez-Diaz, P., Riascos, A., and Moreno, J.
  2nd International Conference on Computing and Data Science, 2021.
  
• A Manifold Learning Data Enrichment Methodology for Homicide Prediction.
  Moreno, J., Dulce-Rubio, M., Riascos, A., Castano, J., and Rodriguez-Diaz, P.
  7th International Conference on Behavioral, Economic and Socio-Cultural Computing (BESC), 2020.
  

Peer Reviewed Workshops

• Efficient allocation of law enforcement resources using predictive police patrolling.
  Rodriguez, P., Dulce M., Moreno, J., Ramirez, S., and Riascos, A.
  LatinX in AI Workshop at NeurIPS, 2019.
  * Best Paper Award
  
• Crime prediction using self-exciting point processes and image features as covariates.
  Dulce, M., Rodriguez, P., Moreno, J., Riascos, A., and Camargo, J.
  LatinX in AI Workshop at NeurIPS 2019.

Other Publications

• Functional linear regression by random projections. (in Spanish)
  Rodriguez-Diaz, P. Advisor: Adolfo J. Quiroz.
  Mathematics Undergraduate Thesis, Universidad de Los Andes, 2018.
  
• Study of the growth of rose cultivation using functional data analysis. (in Spanish)
  Rodriguez-Diaz, P. Advisor: Carlos F. Valencia.
  Industrial Engineering Undergraduate Thesis, Universidad de Los Andes, 2018.

---

Talks and seminars

• LatinX in AI @NeurIPS 2019: Efficient allocation of law enforcement resources using predictive police patrolling. [link to video]
• WiDS Bogota 2020: Using AI as a tool for public security: predictive police patrolling and disrupting human trafficking. (in Spanish) [link to video]
• Atarraya Uniandes: Data Science for Real-World Problems. (in Spanish) [link to video]
• Quantil Applied Mathematics Seminar: Spatio-temporal models with street-level image features for robbery modeling. (in Spanish) [link to video]

---

Media

News Coverage

• IBM DataJam 2019 Winning Project. With technology, young people propose strategies to fight human trafficking, El Espectador. (in Spanish)
• DSSGx UK at The Alan Turing Institute: People Spotlight.

---

Enjoy some of my favorite Colombian landscapes. All pictures are taken by me (or to me).
Enjoy the view!