Back to directoryResource
neuralforecast
Github Repo
by Nixtla
Tags
deep learningforecastingneural networkspythontime series
Continue on SelfMadeQuant
Build the foundations
Suggested foundations for financial time series and financial machine learning. Specialist prerequisites vary by resource.
Before you read
- Stationarity and Unit Roots
Check whether a relationship can be estimated consistently over time.
- Linear Regression
Establish an interpretable baseline before a flexible model.
- Time-Ordered Train, Validation and Test Design
Preserve time order and avoid future information in training.
Go further
- Cointegration and Error Correction
Study long-run relationships without confusing them with correlation.
- Regression Assumptions and Diagnostics
Check the assumptions behind reported estimates.
- Finance-aware validation
Account for dependence and overlapping observations.
Explore a related reading path
- From trading ideas to honest backtests
Choose a reproducible strategy, specify the trading rule, and test what remains after costs and estimation uncertainty.