Hey there, thanks for stopping by!
I’m SayedMorteza (Morteza) Malaekeh, a Ph.D. Candidate in Sustainable Systems Engineering at the University of Texas at Austin, with an M.Sc. in Economics.
My research spans causal inference, representation learning, machine learning, and econometrics, with applications in economics, finance, recommender systems, and sustainability. I develop and apply methods for learning from large-scale, high-dimensional, and multimodal data to understand complex relationships, estimate heterogeneous effects, and support better decisions.
At UT Austin, I work with Prof. Sergio Castellanos in the RESET Lab. My doctoral research examines technology diffusion, household financial outcomes, and environmental benefits, combining causal inference with machine learning and large-scale observational data.
At Lawrence Berkeley National Laboratory, my research examines how residential solar adoption affects household financial well-being. I combine large-scale consumer credit and energy datasets with causal inference to study financial outcomes and how effects differ across households and financing arrangements.
As a Visiting PhD Researcher at Caltech, I worked with Prof. Hannah Druckenmiller on multimodal causal machine learning for environmental economics. This work combines representation learning, imagery, and tabular data to estimate the flood protection benefits of wetlands.
I am seeking academic and industry opportunities starting in 2027, including faculty and postdoctoral positions, research scientist and applied ML roles, data science, and quantitative research.
Research & Publications · Teaching · Talks
Industry Experience
Most recently, I was a PhD Data Science Intern at Roblox, where I worked on the Roblox Moments short-form video recommender system, using causal ML, deep learning, Bayesian optimization, and A/B testing on large-scale behavioral data.
I was also a Quantitative Research Fellow at Quanta Ventures Fund, developing and backtesting systematic trading strategies using machine learning and quantitative methods.
Research & Technical Skills
Causal Inference & Experimentation: Double ML, R-Learner, Causal Forests, Difference-in-Differences, Synthetic Control, A/B Testing, EconML, DoWhy
Machine Learning & AI: Representation Learning, Multimodal Learning, Deep Learning, Recommender Systems, PyTorch, scikit-learn, XGBoost, Bayesian Optimization, LLMs (Hugging Face, LangChain, PEFT/LoRA)
Programming: Python, SQL, R, MATLAB, Stata
Quantitative Finance: Backtesting, Alpha Signals, Time-Series Modeling, Monte Carlo Simulation, Stochastic Processes
Data & MLOps: Spark/PySpark, Hive, Trino, Databricks, Distributed Pipelines, Docker, Kubernetes
Cloud & Compute: AWS, GCP, CUDA, Slurm/HPC, Linux/Bash, Git
Service & Activities
- Program Committee / Reviewer: NeurIPS GenAI for Health
- Reviewer: Agricultural Economics, Theoretical & Applied Climatology, Environmental Monitoring & Assessment
- Board of Directors: Persian Student Society at UT Austin
- Peer Mentor: UT Austin
- Teacher: Yarigaran Education Charity Group
- Basketball Analyst/Writer: 3Sanieh
- Former Varsity Basketball Athlete: Sharif University of Technology