Final Project

CSV Reader node: Loads the bakery sales dataset into KNIME. This is the starting point for analyzing historical sales data to support demand forecasting and inventory decisions.

Removes unnecessary columns (e.g., TransactionNo) and keeps only relevant variables (Items, DateTime, Daypart, DayType) to focus the analysis on meaningful business factors.

Converts the DateTime column into a proper date/time format so it can be used for time-based analysis such as identifying sales patterns by day and hour.

Creates new variables (Day of Week, Hour, Month) from the DateTime column to analyze how sales behavior changes over time.

Aggregates the data to calculate daily sales counts. This creates the key variable (SalesCount) used to analyze how demand varies across different days of the week.

Compares the average daily sales across different days of the week to determine if demand significantly changes depending on the day. This helps identify patterns for better inventory and staffing decisions.

Transforms the data into a contingency table showing how many of each product are sold during different times of the day. This structure is required to analyze relationships between time and product choice.

Counts how many times each product is sold in each time period, creating the summarized data needed for comparison and statistical testing.

Displays the average or total sales for each day of the week, making it easy to compare demand across days. This helps identify peak sales days to improve inventory planning and staffing decisions.

Visualizes how different product categories contribute to total sales over time, showing trends in customer preferences throughout the day. This helps the bakery adjust production to match changing demand patterns.