wrds

Deep learning for forecasting company fundamental data

Calculates 103 firm characteristics from CRSP + Compustat directly in Python – no WRDS SAS cloud

A python script to create a mapping table between I/B/E/S and Compustat

A lightweight Claude Code project for exploring academic literature, brainstorming research ideas, and managing citations. Powered by Corbis MCP.

Research framework for optimal high-frequency market making with Avellaneda-Stoikov quoting, WRDS TAQ replay backtesting, queue-aware fills, volatility-adaptive spreads, and robust execution/P&L analysis.

Pipeline dealing with WRDS (Wharton Research Data Services) datasets including crsp, master, etc, in order to build mega-database for scaling in Market Microstructure research

Interactive research platform for volatility-surface reconstruction, Heston and GBM scenarios, and option-portfolio VaR/ES.

From-scratch replication of Loughran and McDonald (2011) — SEC 10-K sentiment analysis with the LM Master Dictionary, and Fama-MacBeth regressions on filing-period excess returns.

Replication code for "The Shape of Beta: Industry Factor Structure and Crisis Risk Premium" (Woo & Kim, 2026)

Minimal PEAD (post-earnings announcement drift) backtest using Wharton Research Data Services (IBES + CRSP) — Python pipeline for research & plots.

Academically rigorous implementation of the Fama-French (2015) five-factor model using WRDS (CRSP + Compustat) data.

Point-in-time asset-pricing pipeline linking Compustat geographic segments to macro states, CRSP returns, and leakage-aware ML diagnostics.

Point-in-time insider filing de-noising, ML scoring, and cross-sectional return tests.

Replication code for "The Dark Side of Connectivity: How Board Interlock Networks Are Associated with Accounting Risk Through Director Mobility" (Woo & Kim, 2026)

Reinforcement learning for alpha factor discovery, trained on executable backtests against WRDS (CRSP/TAQ) and crypto data.

Academically rigorous implementation of the Fama-French (1993) three-factor model using WRDS (CRSP + Compustat) data.

Option-implied tail-risk connectedness factor research pipeline

Replicate the Loughran and McDonald 2011 sentiment analysis study using 10-K filings and domain-specific financial dictionaries.