ARIMA model from scratch using numpy and pandas.

Familiarization with Higher Order Statistics (Spectra) and ARMA (Autoregressive Moving Average) models. Time Frequency Analysis techniques (Short Time Fourier, Hilbert-Huang and Wavelet Transform) are implemented in ECG signals.

Abstract: The S&P500 is difficult to predict. Multi-factor models provide a useful framework for making returns predictions and for controlling portfolio risk. This paper explores a three-step process in predicting PCA and Autoencoders factors to generate multi-factor models from the S&P500 component securities.

An R package for fitting state-space models to repeated measures of multiple individuals with covariates

Code for the tutorials in the Fickle Heart model calibration with discrepancy 2020 paper.

This is a final project for a Time Series course. My professor told me I could further work on it.

Auto Regressive Models applied on Paris Subway Stations. Time Series Analysis. Predictions of affluence.

Determination the poles of Auto-Regressive Systems in Noise and poles and zeros of Auto-Regressive Moving Average system by SGD in Frequency Domain.

Evaluating different deep learning models to select the best one.

Time Series Data analysis with AR and ARMA models