Methods and apparatus to determine effects of promotional activity on sales
View Patent ↗Example systems, methods, processes, and apparatus for determining expected base sales for a product include obtaining sales data for a product sold at a point of sale location. The sales data can be organized in a time series according to a predetermined time period. The method further includes identifying a promotional event for at least one of the product and the point of sale location and excluding sales data corresponding to the promotional event. The remaining sales data is processed using a smoothed moving average model involving a plurality of passes through the remaining sales data. Expected base data for the product is generated based on the smoothed moving average model and output to a user.
1. A computer-implemented process for determining expected base sales for a sold product, comprising:
obtaining sales data for a product sold at a point of sale location, the sales data organized in a time series according to a time period;
obtaining causal data identifying a promotional event for at least one of the product and the point of sale location;
excluding sales data corresponding to the promotional event to determine a time series of non-promoted sales data for the product;
processing, using a processor, the non-promoted sales data using a double exponentially smoothed moving average model including a smoothing constant that assigns exponentially decreasing weights to older sales data values as the sales data becomes older in time, the processing comprising:
executing a preliminary backward pass through the remaining sales data;
executing a preliminary forward pass through the remaining sales data;
averaging the preliminary backward pass and the preliminary forward pass;
updating the remaining sales data for the product based on second sales data for an additional time period received for the product to provide updated sales data for the product;
executing an updated backward pass through the updated sales data;
executing an updated forward pass through the updated sales data; and
averaging the updated backward pass and the forward pass;
generating, using the processor, expected base data for the product based on the double exponentially smoothed moving average model; and
outputting the expected base data for the product to a user.
2. A process according to claim 1 , further comprising comparing the expected base sales for the product to sales data corresponding to the promotional event to determine incremental sales for the product.
3. A process according to claim 1 , further comprising calculating short and long sales from the remaining sales data based on the averaged backward and forward passes and ignoring outlying short and long sales data points in the time series in the plurality of passes through the remaining sales data.
4. A process according to claim 1 , wherein processing the remaining sales data using the double exponentially smoothed moving average model comprises employing a smoothing constant to provide relative higher weight to newer sales data and relative lower weight to older sales data.
5. A process according to claim 4 , wherein the double exponentially smoothed moving average model comprises an exponentially smoothed moving average model wherein the smoothing constant assigns exponentially decreasing weights as the sales data becomes older in time.
6. A process according to claim 1 , wherein the double exponentially smoothed moving average model is selected based on a determination of trend and seasonality in time series data.
7. A process according to claim 1 , wherein outputting the expected base data for the product to a user further comprises at least one of generating a visual depiction of the expected base data for display to the user and generating a machine-readable representation of the expected base data for further processing.
8. A tangible computer readable storage medium including a program which, when executed, causes a machine to implement a process for determining expected base sales for a sold product, comprising:
obtaining sales data for a product sold at a point of sale location, the sales data organized in a time series according to a time period;
obtaining causal data identifying a promotional event for at least one of the product and the point of sale location;
excluding sales data corresponding to the promotional event to determine a time series of non-promoted sales data for the product;
processing the non-promoted sales data using a double exponentially smoothed moving average model including a smoothing constant that assigns exponentially decreasing weights to older sales data values as the sales data becomes older in time, the processing comprising:
executing a preliminary backward pass through the remaining sales data;
executing a preliminary forward pass through the remaining sales data;
averaging the preliminary backward pass and the preliminary forward pass;
updating the remaining sales data for the product based on second sales data for an additional time period received for the product to provide updated sales data for the product;
executing an updated backward pass through the updated sales data;
executing an updated forward pass through the updated sales data; and
averaging the updated backward pass and the forward pass; and
generating expected base data for the product based on the double exponentially smoothed moving average model.
9. A computer readable storage medium according to claim 8 , wherein the process further comprise comparing the expected base sales for the product to sales data corresponding to the promotional event to determine incremental sales for the product.
10. A computer readable storage medium according to claim 8 , wherein the process further comprises calculating short and long sales from the remaining sales data based on the averaged backward and forward passes and ignoring outlying short and long sales data points in the time series in the plurality of passes through the remaining sales data.
11. A computer readable storage medium according to claim 8 , wherein processing the remaining sales data using the double exponentially smoothed moving average model comprises employing a smoothing constant to provide relative higher weight to newer sales data and relative lower weight to older sales data.
12. A computer readable storage medium according to claim 11 , wherein the double exponentially smoothed moving average model comprises an exponentially smoothed moving average model wherein the smoothing constant assigns exponentially decreasing weights as the sales data becomes older in time.
13. A computer readable storage medium according to claim 8 , wherein the double exponentially smoothed moving average model is selected based on a determination of trend and seasonality in time series data.
14. A computer readable storage medium according to claim 8 , wherein the process further comprises outputting the expected base data for the product to a user by at least one of generating a visual depiction of the expected base data for display to the user and generating a machine-readable representation of the expected base data for further processing.