All About Time Series Pitfalls

The Comprehensive Guide- Part 1

Shrashti Singhal
Towards AI

--

Photo by Jon Tyson on Unsplash

This article is divided into three parts. Part 1 below:

Agenda:

· Time Series Introduction

· Pitfalls: Details, examples & solutions 1–4

INTRODUCTION

Time series problems involve using historical data to make predictions about future events. These problems are commonly found in finance, economics, and engineering. Common techniques for solving time series problems include ARIMA, Exponential smoothing, and Time-series forecasting using Deep Learning techniques like LSTM or Prophet.

1. ARIMA (Autoregressive Integrated Moving Average)

is a statistical model that analyzes and forecasts time series data. It combines autoregression (a model that uses the dependent relationship between an observation and some number of lagged observations) and a moving average model (a model that uses the dependency between an observation and a residual error from a moving average model applied to lagged observations) to make predictions.[2]

2. Exponential smoothing

--

--

No responses yet

What are your thoughts?