{"id":1675160,"date":"2020-09-25T11:38:17","date_gmt":"2020-09-25T18:38:17","guid":{"rendered":"https:\/\/www.retailpro.com\/News\/blog\/?p=1675160"},"modified":"2025-09-17T11:01:35","modified_gmt":"2025-09-17T18:01:35","slug":"predictive-analytics-looking-at-the-past-to-shape-future-sales","status":"publish","type":"post","link":"https:\/\/www.retailpro.com\/News\/blog\/index.php\/2020\/09\/25\/predictive-analytics-looking-at-the-past-to-shape-future-sales\/","title":{"rendered":"Predictive analytics: Looking at the past to shape future sales"},"content":{"rendered":"\n
<\/div>\n\n\n\n
\"\"<\/figure>\n\n\n\n
<\/div>\n\n\n\n

Understanding customer behavior and shopping patterns is difficult enough during \u201cnormal times.\u201d<\/p>\n\n\n\n

So, when a shockwave hits the system \u2013 like a global pandemic or natural disaster \u2013 it stresses the supply chain and puts planning on its ear.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Accounting for seasonality in demand<\/h3>\n\n\n\n
<\/div>\n\n\n\n
\"\"
Image: JESHOOTS.com<\/a><\/figcaption><\/figure>\n\n\n\n
<\/div>\n\n\n\n

Predictive analytics can help retailers prepare for all types of seasonal happenings, including not only holidays, but also hurricanes and wildfires.<\/p>\n\n\n\n

Natural disasters are often seasonal: For example, wildfire season is August-November and hurricane season is slightly longer, starting in June.<\/p>\n\n\n\n

While it is impossible to predict the final landfall point of a hurricane or the path of a wildfire, goods can be procured in a way that optimizes costs while considering all path probabilities.<\/p>\n\n\n\n

Making accurate predictions regarding the types and amounts of products demanded by consumers is not trivial: Ineffective forecasting efforts result in shortages of in-demand products as well as overages of unwanted products that ultimately must be salvaged.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Focusing predictive analytics on concrete business objectives<\/h3>\n\n\n\n
<\/div>\n\n\n\n
\"\"
Image: shattha pilabut<\/a><\/figcaption><\/figure>\n\n\n\n
<\/div>\n\n\n\n

It seems paradoxical that predictive analytics uses historical information to determine future shopper actions.<\/p>\n\n\n\n

Such retail data might include transactions, sales results, customer complaints, and marketing information.<\/p>\n\n\n\n

Retailers use predictive analytics with a business goal in mind. <\/p>\n\n\n\n

By harnessing large, heterogeneous data sets into models, they can glean clear, actionable intelligence that helps them achieve their goals, such as more sales, less inventory, and faster deliveries.<\/p>\n\n\n\n

Having the right data is key to predictive analytics success. That information may include:<\/p>\n\n\n\n