Building a sales prediction model for a retail store

By Pablo Martin, Marina Castaño and Roberto Lopez, Artelnics.

Sales forecasting is an essential task for the management of a store.

Machine learning can help us discover the factors that influence sales in a retail store and estimate the number of sales in the near future.

In this post, we use historical sales data of a drug store chain to predict its sales up to one week in advance.


  1. Data analysis.
  2. Model training.
  3. Testing analysis.
  4. Model deployment.
  5. Conclusions.

Data analysis

The first step of the analysis is to study the data set, which contains the sales information from the drug stores.

The following time series chart shows the number of sales by month.

Sales per month in a retail store

As we can see, the number of sales peaks in July and more so in December. The months with the least sales are January, May, and October.

The following chart shows the distribution of sales throughout the month.

Sales by day of month in a retail store

In this case, the days of the month's beginning and end have higher activity. Around the middle of the month, there is a smaller peak.

It is also essential to look at the number of sales by weekday. The following time series chart shows the sales in these shops from Monday (1) to Sunday (7).

Sales by weekday in a retail store

Monday is the day preferred by the customers to buy in these retail shops. During the rest of the week, the sales decrease from Monday to Thursday and increase on Friday. On Sunday, there is a sharp descent in the number of sales. This is because most of the shops in this drug store chain are closed on this day.

The next step is to select and prepare the variables that we are going to use.

The following list shows the input variables or predictands:

  1. Day of the month.
  2. Month.
  3. Day of the week.
  4. Promotion.
  5. State holidays.
  6. School holidays.
  7. Sales of the 7 previous days.
  8. Promotions of the 7 previous days.

In total, the number of inputs is 20.

The target variable, or predictor is:

  1. Sales of the next seven days.

This is the information that we want to predict with our model.

Model training

After defining the variables that we are going to use for the analysis, it is time to use Neural Designer to build the predictive model for the sales of the stores.

The next image shows a representation of the neural network that we use for the predictive analysis.

Neural network to forecast sales in retail stores

The information on the date, promos, holidays, and sales of the previous week enters the neural network through the left layer. Then, it is analyzed by perceptrons in the middle layer to find the patterns that determine the number of sales given by the last layer.

Now, the neural network is ready to be trained using the Quasi-Newton algorithm. To find more information about this and other optimization algorithms, you can read 5 algorithms to train a neural network.

Testing analysis

Before using the model to forecast the sales, the last step is to determine its predictive power on an independent data set that has not been used before for the training. The next chart shows the linear regression analysis between the scaled output of the neural network and the corresponding scaled targets.

Regression to forecast sales in retail stores

The previous linear regression analysis gives us a correlation coefficient of 0.976 and a slope close to 1. This means the model is predicting well this set of data.

As a consequence, the model is ready to be moved to the deployment phase.

Model deployment

Once we have tested the model, we can predict the shop's sales one week in advance. We introduce the data from the current week as input, and we will obtain the predicted sales for each day of the following week. In the following chart, there is a comparison between the predicted sales applying a promotion or not. The blue line represents the number of sales the model predicts without a promotion, and the orange line is with a promotion. We can see that there is a significant increase.

Retail store sales predictions

As we can see, next week's Monday is when most sales are expected. During the rest of the week, the number of sales will remain stable, and they will decrease on Sunday because of the closing of most stores.


During this article, we have developed a predictive model that can help retailers determine the number of sales they are going to make in the future.

Using this model, retailers can plan the number of products they need. As a consequence, the system will allow them to increase their profits.

You can use Neural Designer to build predictive models from your data and forecast your own company's sales or test it using the data set you can find below.


Related posts: