Objective: Forecast milk prices using Moving Average and Exponential Smoothing methods to analyze trends in agricultural pricing.

Instructions

$1.$ Data Source:

$$ Download historical monthly milk prices from any appropriate series

available at the U$.$S$.$ Department of Agriculture $($USDA$)$ Milk Cost

of Production Estimates.

$$ Ensure the dataset spans at least ten years to capture meaningful

trends.

$2.$ Data Preparation:

$$ Convert the date column to a datetime format and set it as the index.

$$ If necessary, clean the data by filling missing values using forward or

backward fill methods.

$3.$ Exploratory Data Analysis $($EDA$)$:

$$ Plot the milk price time series to observe trends, seasonality, or irregularities.

$$ Describe the main patterns in one or two sentences.

$4.$ Moving Average Forecasting:

$$ Apply a Moving Average model with window sizes of $3,6,$ and $12$

months.

$$ Plot the original series and the smoothed series for each window size.

$$ Briefly discuss the effectiveness of each window size for trend detection.

$5.$ Exponential Smoothing Forecasting:

$$ Apply Single Exponential Smoothing and Double Exponential Smoothing

methods.

$$ Plot the forecasts on the same graph as the original series.

$$ Compare the methods and note which is more responsive to recent

price changes.

$6.$ Evaluation:

$$ Calculate the Mean Absolute Error $($MAE$)$ or Mean Squared Error

$($MSE$)$ for each forecasting method.

$$ Summarize your findings on the most effective technique for this

dataset.