terence-lim / financial-data-science

Financial and Investment Data Science: FinDS Python library and examples for applying quantitative and machine learning methods on structured and unstructured financial data sets

Financial Data Science

The FinDS package comprises Python modules for maintaining large structured and unstructured financial data sets, and exploring quantitative and machine learning methods

Resources

1. Online Jupyter-book, or download pdf

2. FinDS API reference

3. FinDS repo

4. Jupyter notebooks repo

Examples

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

Contact

Github: https://terence-lim.github.io