Welcome to My Webpage!
PhD Candidate in Economics with joint affiliation in Computer Science
I bridge economic theory with computational methods, specializing in machine learning, econometric modeling, and data science to solve complex problems. Seeking to leverage my interdisciplinary expertise as an Applied Scientist/Economist in industry.
Research Projects
📈 Economics Research
Market Segmentation Under Costly Information Acquisition
This paper investigates third-degree price discrimination under endogenous market segmentation. Segmenting a market requires access to information about consumers, and this information comes with a cost. I explore the trade-offs between the benefits of segmentation and the costs of information acquisition, revealing a non-monotonic relationship between consumer surplus and the cost of information acquisition for monopolist. I show that in some markets, allowing the monopolist easier access to customer data can also benefit customers on average. I also analyzed how social welfare reacts to changes in the cost level of information acquisition and showed that the non-monotonicity result is also valid in social welfare analysis. This result can be considered a good caveat for policymakers who focus on market efficiency.
23rd Annual International Industrial Organization Conference (IIOC)
Efficiency and Policy Trade-offs in Washington State Timber Auctions
Created a comprehensive dataset from unstructured 5,000+ single-sale PDF data by implementing Amazon Textract for structured data extraction and integrating the OpenAI API for advanced text processing and classification. Developed and calibrated a structural econometric model analyzing efficiency-policy optimality trade-offs in Washington State timber auctions, quantifying the economic impacts of auction design choices. Conducted counterfactual analysis of alternative auction designs and policies, assessing welfare and strategic behavior outcomes.
💻 Computer Science Projects
Matching Algorithms
Developed and published a comprehensive Python package implementing a variety of matching algorithms, including the Deferred Acceptance algorithm, the Boston Mechanism, the Top Trading Cycles (TTC) mechanism, and several linear programming approaches. This open-source library is widely applicable in various domains such as school admissions, job assignments, and resource allocation problems. The package's effectiveness in creating stable and efficient matchings makes it a valuable tool for researchers and practitioners in economics, computer science, and operations research.
Install with: pip install matching-algorithms
🔤 NLP: Dialogue Segmentation
In this paper, we delve into the task of classifying conversation segment breaks using various Natural Language Processing (NLP) models. We leverage the rich textual data within the GUIDE dataset to identify these transitions. We have worked with a couple of baseline models alongside some ad- vanced models like SpanBERT and RoBERTa to assess their effectiveness in dialogue segmenta- tion. We further experiment with optimization tech- niques to refine model performance. This analysis gives some insights for the future advancements in dialogue understanding and the development of more sophisticated conversation analysis systems.
🐦 NLP: Election Sentiment Analysis
Twitter sentiment analysis for election prediction and political opinion mining. Advanced text preprocessing, feature engineering, and machine learning models for real-time sentiment tracking during electoral campaigns.
🖼️ Computer Vision: Medical AI
Developed and optimized a deep learning pipeline for automated breast mass segmentation using a U-Net convolutional neural network (CNN) architecture in PyTorch, leveraging AWS for scalable machine learning workflows and deploying Weights & Biases to systematically monitor and visualize training outputs for precise performance tracking and advanced hyperparameter optimization; achieved a 0.86 Dice coefficient when validating against 12,000 mammogram images, representing a 15% performance improvement over previous approaches.
Technical Expertise
Get In Touch
Open to quantitative research roles in economics, finance and policy analysis.