MULTILAYER_PERCEPTRON

A Multilayer Perceptron (MLP) is a type of feedforward artificial neural network (ANN) used for time series forecasting. and falls under Deep Learning, which is a subset of Artificial Intelligence (AI). Unlike traditional models like ARIMA, MLPs can learn complex non-linear patterns in data.

🚀 Unlike LightGBM and XGBoost, which are classical machine learning models, MLP is a deep learning model that learns patterns through multiple layers of neurons

🔹 MLP Architecture for Time Series Forecasting

An MLP consists of:

✅ Input Layer → Takes past time series values as features

✅ Hidden Layers → Process the data using activation functions

✅ Output Layer → Predicts future values

MLPs work well with structured time series, but they do not inherently capture sequential dependencies like LSTMs or RNNs.