The FinDS package comprises Python modules for maintaining large structured and unstructured financial data sets, and exploring quantitative and machine learning methods
notebook | Financial | Data | Science |
---|---|---|---|
stock_prices | Stock distributions, delistings | CRSP stocks | Sample selection |
jegadeesh_titman | Overlapping portfolios; Momentum |
CRSP stocks | Hypothesis testing; Newey-West correction |
fama_french | Bivariate sorts; Value, Size; CAPM |
CRSP stocks; Compustat |
Linear regression; Quadratic programming |
fama_macbeth | Cross-sectional Regressions; Beta |
Ken French data library | Feature transformations; Kernel regression, LOOCV |
weekly_reversals | Mean reversion; Implementation shortfall |
CRSP stocks | Structural break tests |
quant_factors | Factor zoo; Performance evaluation |
CRSP stocks; Compustat; IBES |
Clustering for unsupervised learning |
event_study | Event studies | S&P key developments | Multiple testing; FFT |
economic_releases | Macroeconomic analysis; Unemployment |
ALFRED | Economic data revisions |
regression_diagnostics | Regression analysis; Inflation |
FRED | Linear regression diagnostics; Residual Analysis |
econometric_forecast | Time series analysis; National Output |
FRED | Stationarity, Autocorrelation |
approximate_factors | Approximate factor models | FRED-MD | Unit Root; PCA; EM Algorithm |
economic_states | State space models | FRED-MD | Gaussian Mixture; HMM; Kalman Filter |
conditional_volatility | Value at risk; Conditional volatility |
FRED cryptos and currencies | ARCH, GARCH; VaR, TVaR |
covariance_matrix | Covariance matrix estimation; Portfolio risk |
Ken French data library | Shrinkage |
term_structure | Interest rates, yield curve | FRED | Splines, PCA |
bond_returns | Bond portfolio returns | FRED | SVD |
option_pricing | Binomial trees; the Greeks |
OptionMetrics; FRED |
Simulations |
market_microstructure | Liquidity costs; Bid-ask spreads |
TAQ tick data | Realized volatility; Variance ratio |
event_risk | Earnings surprises | IBES; FRED-QD |
Poisson regression; GLM's |
customer_ego | Principal customers | Compustat customer segments | Graph Networks |
bea_centrality | Input-output use tables | Bureau of Economic Analysis | Graph centrality |
industry_community | Industry sectors | Hoberg&Phillips data library | Community detection |
link_prediction | Product markets | Hoberg&Phillips data library | Links prediction |
spatial_regression | Earnings surprises | IBES; Hoberg&Phillips data library |
Spatial regression |
fomc_topics | Fedspeak | FOMC meeting minutes | Topic modelling |
mda_sentiment | Company filings | SEC Edgar | Sentiment analysis |
business_description | Growth and value stocks | SEC Edgar | Part-of-speech tagging |
classification_models | News classification | S&P key developments | Classification for supervised learning |
regression_models | Macroeconomic forecasting | FRED-MD | Regression for supervised learning |
deep_classifier | News classification | S&P key developments | Feedforward neural networks; Word embeddings; Deep averaging |
convolutional_net | Macroeconomic forecasting | FRED-MD | Temporal convolutional networks; Vector autoregression |
recurrent_net | Macroeconomic forecasting | FRED-MD | Elman recurrent networks; Kalman filter |
fomc_language | Fedspeak | FOMC meeting minutes | Language modelling; Transformers |
reinforcement_learning | Spending policy | Stocks, bonds, bills, and inflation | Reinforcement learning |
Github: https://terence-lim.github.io