Abstract: A device may receive customer data, and may identify unique communication channels associated with the customer data. The device may determine, based on the customer data, an optimal order for a Markov chain model, and may determine a model accuracy of the Markov chain model based on the optimal order. The device may transform transitions in the Markov chain model, based on the customer data, to generate transformed transitions, and may process the customer data, with a multi-level indexing model and based on the unique communication channels and the transformed transitions, to generate sparse matrices. The device may determine removal effects and steady state values for the sparse matrices, and may determine attribution weights for the unique communication channels based on the Markov chain model with the optimal order, the removal effects, and the steady state values. The device may perform actions based on the attribution weights.

Abstract: A device may receive customer data, and may identify unique communication channels associated with the customer data. The device may determine, based on the customer data, an optimal order for a Markov chain model, and may determine a model accuracy of the Markov chain model based on the optimal order. The device may transform transitions in the Markov chain model, based on the customer data, to generate transformed transitions, and may process the customer data, with a multi-level indexing model and based on the unique communication channels and the transformed transitions, to generate sparse matrices. The device may determine removal effects and steady state values for the sparse matrices, and may determine attribution weights for the unique communication channels based on the Markov chain model with the optimal order, the removal effects, and the steady state values. The device may perform actions based on the attribution weights.

Abstract: A device obtains data, for a current media plan, that includes a cost adjustment factor, a duration of an unexecuted portion of the current media plan that is divisible into periods of time, and an unutilized budget, for the duration, that is divisible into budget portions based on the periods of time. The device generates a predictive baseline cost parameter by adjusting, by the cost adjustment factor, a baseline cost parameter of a previously implemented baseline media plan. The device predicts cost metrics for the current media plan using the predictive baseline cost parameter, and predicts performance metrics for the current media plan based on the cost metrics and predictive baseline cost parameter. The device determines target cost per point (CPP) values for the current media plan based on the cost metrics and performance metrics, and causes an action to be performed based on the target CPP values.

Abstract: A device obtains data, for a current media plan, that includes a cost adjustment factor, a duration of an unexecuted portion of the current media plan that is divisible into periods of time, and an unutilized budget, for the duration, that is divisible into budget portions based on the periods of time. The device generates a predictive baseline cost parameter by adjusting, by the cost adjustment factor, a baseline cost parameter of a previously implemented baseline media plan. The device predicts cost metrics for the current media plan using the predictive baseline cost parameter, and predicts performance metrics for the current media plan based on the cost metrics and predictive baseline cost parameter. The device determines target cost per point (CPP) values for the current media plan based on the cost metrics and performance metrics, and causes an action to be performed based on the target CPP values.