Home Math for a better future

Chi siamo La nostra identità

Soluzioni La matematica per evolvere

Casi studio Esempi di storie di successo

Education La formazione su misura

Contattaci Il filo diretto con gli specialisti

Home

Chi siamo

Soluzioni

Casi studio

Education

Contattaci

Magazine Unisciti a noi

Solution

Propensity

x + by + cz + d = 0 a (f(x + T) = f(x), ∀ x ∈ IR) (f(−x) = f(x), ∀ x ∈ D) −x + 2y + z + t = −1 2x + 2y + z + 4t = 0 C = {z = x + iy x, y ∈ IR} z = −1 + i nα = θ + 2πk

Propensity

Response Prediction

Acquiring a new customer costs much more than retaining an existing one. Satisfying and protecting the customer base is essential to the profitability of a business, but it is not always easy to manage. In fact, competitor acquisition campaigns are often aggressive and, having a very large customer base, it is complex to keep satisfaction levels monitored and recognize the risk of churn. At the same time, it is necessary to plan customer retention campaigns in a targeted way that optimizes the use of time and resources.

x + by + cz + d = 0 a (f(x + T) = f(x), ∀ x ∈ IR) (f(−x) = f(x), ∀ x ∈ D) −x + 2y + z + t = −1 2x + 2y + z + 4t = 0 C = {z = x + iy x, y ∈ IR} z = −1 + i nα = θ + 2πk

Propensity/Response Prediction allows to identify which users are at the highest risk of churn and where it is useful and necessary to act promptly with prevention actions. Our solution can simulate the effectiveness of actions in terms of positive response from the customer and simplify the work of customer care.

High precision

Both in data analysis and in campaign forecasting

Decreased churn rate

Thanks to the rapid identification of customers at higher risk of churn

More effective retention campaigns

Thanks to the simplification of customer care effort through more accurate and specific information

Examples

Sectors

Application examples of Response Prediction

Products

Simulating the customer base response to a new product to identify those who will respond positively

Utilities

Predicting customers with the highest risk of churn and simulating different prevention or win-back campaigns to identify the most suitable ones for each customer

Services

In the nonprofit sector, predicting the donors with the highest risk of churn and simulating different upgrade campaigns to identify the most promising ones for each customer

Deepening

Operating logic

Our solution is based on a machine learning algorithm that, starting from the data that tells the story of each customer (e.g. past purchases, payment times and methods, interactions on different touchpoints, outcome of past campaigns, etc.), allows to predict the probability of a customer leaving the company within a certain period of time and to simulate the effectiveness of a given campaign.

Method