Concept drift is a significant challenge in machine learning, particularly in nonstationary environments where the data distribution changes over time. Effective detection requires balancing robustness to noise with sensitivity to drift. Visualization has become a key tool for explainable AI, helping in the intuitive understanding of data changes. Concept drift visualization specifically helps in the descriptive analysis of data with changing statistical properties over time. This paper introduces a novel interactive visualization model based on Shifted Colocated Paired Coordinates (SCPC), to detect and explain concept drift. SCPC combines the strengths of Shifted Paired Coordinates and Colocated Paired Coordinates to represent the first two moments of probability distributions in a lossless manner. By applying SCPC to synthetic and real-life datasets, we demonstrate its effectiveness in visualizing concept drift, pinpointing drift occurrences, and aiding in understanding data variability. Our approach allows the users to explore and identify concept drift in a detailed and intuitive manner.