Abstract: The embodiments the systems and methods described herein attempt to optimally select a group or portfolio of control locations for each test location. The optimization can be generally performed in two steps. First, an objective function is defined that scores the similarity of a set of control locations averaged together. Second, given the large number of potential solutions, a computationally-feasible algorithm that identifies an optimal set of control locations and is based on the objective function is executed. In order to obtain the optimal set of control locations in an efficient manner for use in business analytics, the algorithm may use a hill-climbing algorithm. As a result, an optimization function can be incrementally improved in an efficient manner.

Abstract: The systems and methods perform simulations in a systematic way as to minimize redundant data fetching and computations and reduce run-time. The systems and methods can cache information that can be used across multiple control strategies and speed up the process of simulation by several orders of magnitude. A business analyst can first generate a set of matching criteria that meets business intuition for the specific initiative and set of stores under analysis. A systematic approach in building similar sites models from control strategies that are combinations of this set of matching criteria can be applied to minimize data extraction and processing. The similarity function allows for the distance of each criterion to be combined linearly. Data for each matching criteria only needs to be extracted once but can be used in all control strategies that uses that criteria.

Abstract: The computer system and method described herein attempt to address the deficiencies by analyzing all relevant data points for each test and control location collectively determine outliers and then exclude the individual outlier data points from the data when analyzing an initiative during a relevant test period. Rather than exclude outliers at the site level, the particular time increment having the outlier data can be extracted and the site can remain in the analysis.

Abstract: The embodiments the systems and methods described herein attempt to optimally select a group or portfolio of control locations for each test location. The optimization can be generally performed in two steps. First, an objective function is defined that scores the similarity of a set of control locations averaged together. Second, given the large number of potential solutions, a computationally-feasible algorithm that identifies an optimal set of control locations and is based on the objective function is executed. In order to obtain the optimal set of control locations in an efficient manner for use in business analytics, the algorithm may use a hill-climbing algorithm. As a result, an optimization function can be incrementally improved in an efficient manner.

Abstract: The methods and systems described herein attempt to address the above-mentioned need by providing an algorithm and software capability to automatically detect and assess “natural experiments” that exist in any underlying dataset. In one embodiment, a computer-implemented method for identifying an experiment to use in an analysis of a business initiative comprises storing, by a computer, a set of historical data regarding entities in a business network; receiving, by the computer, a selection of inputs for the historical data; detecting, by the computer, a natural experiment based upon changes in the discretized historical data; and outputting, by the computer, a report of a detected experiment from the discretized historical data.

Abstract: The methods and systems described herein attempt to address the above-mentioned need by providing an algorithm and software capability to automatically detect and assess “natural experiments” that exist in any underlying dataset. In one embodiment, a computer-implemented method for identifying an experiment to use in an analysis of a business initiative comprises storing, by a computer, a set of historical data regarding entities in a business network; receiving, by the computer, a selection of inputs for the historical data; detecting, by the computer, a natural experiment based upon changes in the historical data; and outputting, by the computer, a report of a detected experiment from the historical data.

Abstract: The systems and methods described herein attempt to capture the impact on both the promoted items and other related products. The systems and methods analyze attached sales impact only for items that are more likely to be purchased with the featured product. The systems and methods also allow for measuring a cannibalization impact by analyzing the impact on potential cannibalized products and items that are more likely to be purchased with the cannibalized products. By aggregating the promoted impact and cannibalized impact, including the items with strong co-selling relationships, a full picture of the promotion can be obtained. Further, combining the item-level results into custom groupings can allow for further business insights.

Abstract: The systems and methods perform simulations in a systematic way as to minimize redundant data fetching and computations and reduce run-time. The systems and methods can cache information that can be used across multiple control strategies and speed up the process of simulation by several orders of magnitude. A business analyst can first generate a set of matching criteria that meets business intuition for the specific initiative and set of stores under analysis. A systematic approach in building similar sites models from control strategies that are combinations of this set of matching criteria can be applied to minimize data extraction and processing. The similarity function allows for the distance of each criterion to be combined linearly. Data for each matching criteria only needs to be extracted once but can be used in all control strategies that uses that criteria.

Abstract: The methods and systems described herein attempt to address the above-mentioned need by providing an algorithm and software capability to automatically detect and assess “natural experiments” that exist in any underlying dataset. In one embodiment, a computer-implemented method for identifying an experiment to use in an analysis of a business initiative comprises storing, by a computer, a set of historical data regarding entities in a business network; receiving, by the computer, a selection of inputs for the historical data; detecting, by the computer, a natural experiment based upon changes in the historical data; and outputting, by the computer, a report of a detected experiment from the historical data.

Abstract: The systems and methods described herein attempt to capture the impact on both the promoted items and other related products. The systems and methods analyze attached sales impact only for items that are more likely to be purchased with the featured product. The systems and methods also allow for measuring a cannibalization impact by analyzing the impact on potential cannibalized products and items that are more likely to be purchased with the cannibalized products. By aggregating the promoted impact and cannibalized impact, including the items with strong co-selling relationships, a full picture of the promotion can be obtained. Further, combining the item-level results into custom groupings can allow for further business insights.

Abstract: The computer system and method described herein attempt to address the deficiencies by analyzing all relevant data points for each test and control location collectively determine outliers and then exclude the individual outlier data points from the data when analyzing an initiative during a relevant test period. Rather than exclude outliers at the site level, the particular time increment having the outlier data can be extracted and the site can remain in the analysis.

Abstract: The systems and methods perform simulations in a systematic way as to minimize redundant data fetching and computations and reduce run-time. The systems and methods can cache information that can be used across multiple control strategies and speed up the process of simulation by several orders of magnitude. A business analyst can first generate a set of matching criteria that meets business intuition for the specific initiative and set of stores under analysis. A systematic approach in building similar sites models from control strategies that are combinations of this set of matching criteria can be applied to minimize data extraction and processing. The similarity function allows for the distance of each criterion to be combined linearly. Data for each matching criteria only needs to be extracted once but can be used in all control strategies that uses that criteria.

Abstract: The systems and methods described herein can index the economic activity in a trade area of a location by identifying a set of data concerning the economic activity of a plurality of locations and storing it with the associated geographic position of each of the locations. A geographic trade area is then determined for each of the locations, using either a pre-set area defined as a radius from the location or through input by a user. The database is queried to identify all of the locations within the trade area of the subject location. The economic activity associated with the locations is aggregated and compared across time periods to create the index of the economic activity within the subject location's trade area. The economic activity from these locations may also be weighted by any number of factors, including distance from the subject location, and type of retailer.

Abstract: A system, method, and article of manufacture is disclosed for determining optimal parameter settings for a business initiative testing model used for testing initiatives for business locations included in a business network. In one aspect, a method is disclosed that includes defining a first test type of a business initiative testing model having a set of parameter settings. Each parameter setting may include a set of one or more parameter setting options. The method may also include performing virtual tests on a set of virtual test sites based on the defined test type. Each virtual test site may reflect a selected business location in the business network. Also, the method may include determining a set of optimal parameter settings for the first test type of the business initiative testing model based on results from the virtual test.

Abstract: A system, method, and article of manufacture is disclosed for developing and managing a the test of a business initiative for a business network including business locations. In one aspect of the invention, a method is performed that includes performing a process for developing a business initiative to apply to the business network and performing a process for designing a test for the initiative. Further, the method includes executing the initiative at a set of test sites in accordance with the designed test, each test site corresponds to a selected business location in the business network. Also, performance results of the executed initiative may be analyzed and a rollout plan is created for implementing the initiative at a first set of business locations.

Abstract: A system, method, and article of manufacture is disclosed for determining optimal parameter settings for a business initiative testing model used for testing initiatives for business locations included in a business network. In one aspect, a method is disclosed that includes defining a first test type of a business initiative testing model having a set of parameter settings. Each parameter setting may include a set of one or more parameter setting options. The method may also include performing virtual tests on a set of virtual test sites based on the defined test type. Each virtual test site may reflect a selected business location in the business network. Also, the method may include determining a set of optimal parameter settings for the first test type of the business initiative testing model based on results from the virtual test.