FinancialDataLoader<T>

Models & Types · AiDotNet.Finance.Data

Data loader for financial time series forecasting.

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → FinancialDataLoader<T>

For Beginners

This loader creates training samples like:

  • Input: the last N time steps (lookback window)
  • Output: the next M time steps (prediction horizon)

It handles batching, shuffling, and splitting into train/val/test.

How It Works

FinancialDataLoader turns a list of OHLCV points into windowed tensors suitable for training forecasting models. It implements the standard InputOutputDataLoader API so it works with AiDotNet’s training pipeline.

Constructors

Constructor Summary
FinancialDataLoader(IReadOnlyList<MarketDataPoint<T>> series, int sequenceLength, int predictionHorizon, bool includeVolume, bool includeReturns, bool predictReturns, bool normalizeMinMax, FinancialPreprocessor<T> preprocessor, int batchSize) Creates a new financial data loader.

Properties

Property Summary
int FeatureCount { get; }
int OutputDimension { get; }
int TotalCount { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed)