An e$-$commerce platform wants to improve its recommendation system by understanding customer behavior. Discuss how you would use measures of central location $($mean$,$ median, mode$)$ and measures of dispersion $($range$,$ variance, standard deviation$)$ to gain insights into customer purchase data. Explain how these statistical techniques can help in making data$-$driven decisions. How would you handle outliers in this context, and what impact might they have on your analysis?