STATISTICAL ANALYSIS OF ONLINE SALES DATA TO PREDICTION CONSUMER SHOPPING TRENDS

Abstract

In the context of online business, understanding the relationship between product price and the quantity sold poses a significant challenge in optimizing marketing strategies and enhancing profitability. Setting the right price can be the key to success in maintaining competitiveness and meeting the increasingly complex needs of consumers in this digital era. This research aims to analyze the relationship between product price and quantity sold in online businesses and to predict consumer shopping trends based on product prices.The methods used in this study include descriptive statistical analysis and linear regression. Descriptive statistical analysis is employed to identify patterns and trends in online sales data, while linear regression is used to analyze the relationship between product price and quantity sold and to predict consumer shopping trends. Online sales data are analyzed across various variables, including quantity sold, product price, and transaction time. The results of descriptive statistical analysis indicate significant variation in the quantity sold, with an average of approximately 59.91 and an average product price of Rp 393,732. Scatter plot visualization of the data reveals a pattern where products with lower prices tend to have higher sales, while products with medium to high prices tend to exhibit lower sales variability. Furthermore, the results of linear regression show a tendency for sales to decline with increasing product prices. The predictive model built has a low error rate, with a Mean Squared Error (MSE) of 383.45, indicating the model's ability to predict the quantity of products sold based on product prices.
Keywords: online business, product price, quantity sold, marketing strategy, consumer shopping trends.