Finance

# Autoregressive Integrated Moving Average (ARIMA)

Autoregressive Integrated Moving Average (ARIMA)

Statistical models have become increasingly valuable as the quantity and diversity of data have continued to increase. One such model is ARIMA, also known as Auto-Regressive Integrated Moving Average, which is significant in the field of data science and machine learning. It forecasts by regressing past results, but it does not necessarily require specialized statistical expertise. It can be designed with minimal data and can be easily created, introduced, and evaluated.

The Autoregressive Integrated Moving Average(ARIMA) model makes future predictions by interpreting time-series data and statistical analysis. The ARIMA model aims to explain data by using time-series data on its past values and uses linear regression to make predictions. An autoregressive integrated moving average is a form of regression analysis that gauges the strength of one dependent variable relative to other changing variables. The goal of this model is to predict future changes in financial markets or securities by examining the difference between values in series instead of through model values.

Key Components:

• Autoregression (AR) – It refers to a model that shows a changing variable that regresses on its own lagged, or prior, values.
• Integrates (I) – It represents the differencing of raw observation to allow for the series to become stationary, i.e, data values are replaced by the difference between the data values and the previous value
• Moving Average (MA) – It incorporates the dependency between an observation and a residual error from a moving average model applied to lagged observations.

Application of the ARIMA model:

The Autoregressive Integrated Moving Average(ARIMA) model can be used to forecast future quantities (or even prices) based on historical data in business & finance. The data must be reliable and must show a relatively long period over which it has been collected so that the model can be reliable. Some of the applications of the ARIMA model in business are as below:

• Forecasting the number of goods needed for the next period based on historical data.
• Forecasting sales and interpreting seasonal changes in sales.
• Estimating the impact of marketing events, new product launches, and so on.

Python and R like data analytics and data software can be used to create ARIMA models.

Limitations of ARIMA models:

Although ARIMA models can be highly accurate and reliable under the appropriate conditions and data availability, one of the key limitations of the model is that the parameters (p, d, q) need to be manually defined. Hence, finding the most accurate fit can be a trial and error process.

Similarly, the model depends highly on the reliability of the difference between the data and historical data. It is important to ensure that data was collected accurately and over a long period so that the model provides accurate results and forecasts.

Final Thoughts:

The ARIMA model is typically denoted with (p, d, q) which can be assigned with different values to modify the model and apply it in different ways. Some of the limitations of the model are its dependency on a manual trial and error process and data collection required to determine parameter values that fit best.

Author – Hariharan Krishnan

About the Author – Hariharan Krishnan is currently in second year BAF and is also doing FRM part 1. He is passionate about financial markets and loves to play chess and outdoor games.

Related post:

Delta Hedging

Correlation in Financial Market