Result: Predicting Customer Satisfaction Score (CSS) for Urban Company Utilizing the K-Nearest Neighbours (KNN) Algorithm: A Machine Learning Approach

Urban Company is one of the leading hyperlocal online home service providers connecting service providers with service seekers and relies heavily on customer satisfaction to maintain its reputation and competitiveness in the market. Understanding and predicting customer satisfaction levels are crucial for Urban Company to enhance its services and retain loyal customers. This study uses a machine learning approach using the K-Nearest Neighbors (KNN) algorithm to predict customer satisfaction on the Urban Company platform. The SERVQUAL model for assessing service quality based on five dimensions: Tangibles, Reliability, Responsiveness, Assurance, and Empathy acts as the input factor and the calculated Customer Satisfaction Score (CSS) using Root Mean Square (RMS) acts as the output parameter. A total of 514 survey data were collected, and its corresponding CSS value was calculated. From the survey, 80% of the data was used to train the model, and 20% was used for testing the model. The model underwent evaluation utilizing Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) metrics. Subsequently, the discrepancy between the actual and predicted CSS was assessed via the KNN algorithm, revealing a Root Mean Squared Error of 3.14 and a Mean Absolute Error of 1.92 which is beneficial for the Urban Company to understand its customer satisfaction level in various scenarios and to retain loyal customers.