case history
A company offering a cloud-computing service provides any customers request of computing resources (processors, virtual memory, disk space). The company has to satisfy two competitive needs: one is to provide the proper hardware available to fulfil any requests and the necessity to not leave a large number of unused machines. In order to achieve the requirements, it is crucial to have a rational prediction exploiting all the information available and indicating the likelihood of receiving a set of requests in a specific time period. It is possible to model the flux of customers requests and infer from archived data the rate of arrival of a request, and its features. The Bayesian approach is an extremely powerful tool to model the prediction and provides results of clear interpretation. By studying the history of all requests and knowing the resources available, Pangea Formazione has developed a model that simulates (using Monte Carlo techniques) scenarios for the near future requests. In addition, the tool has a graphical interface allowing the user to estimate the time interval where the currently available resources will be fulfilled and the likelihood of meeting the requests in a given time. The company supported by this predictive tool can rationally determine when it is time to enhance the machine fleet. Moreover, the tool allows to quantitatively manage the risk of delaying the service delivery to specific customers and compare it to the cost of a purchase of other machines.

Using a bayesian approach, Pangea Formazione was able to forecast the energy produced by solar farms. The analysis of past data allowed to link weather conditions to both solar radiation and the performance of photovoltaic systems, thus getting a reliable forecast about the production of energy in the next future. This result is crucial for the sale and offer in the energy market.

Pangea Formazione worked in collaboration with an Italian industry to analyse the reliability of the components productive processes and to monitor the synergy of the industrial processes. This was done using the Bayesian approch as a powerful tool to infer cause-effect relationships.

Pangea Formazione's support was requested to make previsions regarding cost-revenue benefits derived from commercial agreements between more than 200 foreign partners. The Bayesian approach applied to the prevision of influential business variables allowing the exploitation of profitable opportunity.

Using a Bayesian network based technique, Pangea Formazione provided an important contribution to the customer website optimisation, with the aim to make surfing more productive and user-friendly.

Pangea Formazione provided rational previsions on the amount of virtual machine requests in the near future, in order to speed up the delivery process to the customer.

Pangea Formazione provided support to the activity of fraud detection and prevention by exploiting several techniques such as Bayesian network and artificial intelligence algorithms.

Pangea Formazione developed a prevision model of call traffic based on Bayesian inference. This tool was devised as a functional support for the negotiation activity between operators, and it revealed to be a useful support to clients offers planning.

È preferibile prevedere anche senza certezza alcuna,
che non prevedere affatto
Henri Poincare

This website uses cookies to allow us to see how the site is used. The cookies cannot identify you. Cookies are files stored in your browser and are used by websites to help personalise your web experience. By continuing to use our website without changing the settings, you are agreeing to our use of cookies. However you can change your cookie settings at any time.