This paper evaluated the efficiency of four clustering models named, density-based spatial clustering of applications with noise, agglomerative clustering, k-means clustering, and random forest clustering using K-means algorithm. It also analyzed five time-series models, Naïve forecasts, simple exponential smoothing, moving average, Holt’s exponential smoothing, and Holt–Winters exponential smoothing. The experiment was carried out on a publicly available dataset named, Global Super Store, collected from Kaggle. The clustering models were evaluated using the Davies–Bouldin index, and Silhouette score and the time-series models were examined using mean square error, mean absolute percentage error, and R-squared value. Random forest clustering demonstrated outstanding performance in clustering distinct group of client segments, as evidenced by very high Silhouette score and significant Davies–Bouldin index. Holt–Winters, by capturing trend and seasonality, proved to be the most effective among the five time-series models, yet not sufficient for accurate prediction. The study discussed the importance of these findings for business organizations and suggested advanced deep learning model for forecasting time-series data.