Forecasting and Time Series Analysis

Vocabulary flashcards covering fundamental concepts, components, methods, and error metrics of forecasting and time series data.

Forecasting

Estimating a future value using information from the past.

Time Series Data

A set of observations recorded in chronological order, meaning the data is arranged according to time.

Forecasts Based on Time-Series Data

The process of analyzing time series data using statistics and modeling to make predictions and inform strategic decision-making.

Planning (Forecasting Importance)

Helps businesses prepare for expected sales, demand, and expenses.

Budgeting (Forecasting Importance)

Helps determine how much money will be needed and where it should be spent.

Managing Inventory (Forecasting Importance)

Helps avoid having too much or too little stock.

Reducing Risks (Forecasting Importance)

Helps anticipate possible problems and prepare for them.

Trends

The long term direction of data over an extended period (upward, downward, or stationary).

Seasonality

Patterns that repeat at a specific and predictable time.

Cyclical Variation

Long term wave like patterns tied to economic or business cycles, lacking a fixed duration.

Irregular Variation

Unexpected or unpredictable changes or events.

Naive Method

A forecasting method that assumes the next period's value will be the same as the most recent value.

Simple Moving Average

A forecasting method that estimates future values by taking the arithmetic mean of a specific number of the most recent actual values.

Weighted Moving Average

A forecasting method that assigns custom weight to past periods, usually giving more emphasis to recent data. The sum of all weights must equal to $1$ or $100\%$.

Exponential Smoothing

A forecasting method that adjusts the previous forecast based on the most recent actual value.

Trend Projection

A forecasting method used when data shows a clear upward or downward trend.

Forecast Error

The difference between the actual value and the forecast ($\text{F.E.} = \text{A.V.} - \text{F.V.}$).

Mean Absolute Deviation

Calculates the average absolute error.

Mean Squared Error

Calculates the average of the squared errors.

Mean Absolute Percentage Error

Calculates the average absolute percentage error.