Pay-per-click advertising includes various formats (e.g., search, contextual, and social) with a total investment of more than 140 billion USD per year. An advertising campaign is composed of some subcampaigns-each with a different ad-and a cumulative daily budget. The allocation of the ads is ruled exploiting auction mechanisms. In this paper, we propose, for the first time to the best of our knowledge, an algorithm for the online joint bid/budget optimization of pay-per-click multi-channel advertising campaigns. We formulate the optimization problem as a combinatorial bandit problem, in which we use Gaussian Processes to estimate stochastic functions, Bayesian bandit techniques to address the exploration/exploitation problem, and a dynamic programming technique to solve a variation of the Multiple-Choice Knapsack problem. We experimentally evaluate our algorithm both in simulation-using a synthetic setting generated from real data from Yahoo!-and in a real-world application over an advertising period of two months.

Telemedicine is the combination of technologies and activities that offer new remote ways of medical care. The Sm@rtEven application project is a remote assistance service that follows patients affected by lower limb fractures surgically treated at Galeazzi Orthopedic Institute (Milan, Italy). The Sm@rtEven application aims to evaluate the clinical conditions of patients treated for lower limb fracture after discharge from hospital using remote follow-up (FU). The project is not a substitute for traditional clinical consultations but an additional tool for a more complete and prolonged view over time. The Sm@rtEven application is installed on patients’ smartphones and is used daily to communicate with healthcare personnel. In the first protocol, patients had to complete different tasks for 30 days, such as monitoring the load progression on the affected limb, the number of steps during the day, and body temperature and completing a questionnaire. A simplified protocol was proposed due to the pandemic and logistical issues. The revised protocol enrolled patients after more than 30 days of their operation, prioritized the rehabilitation phase, and required patients to use the app for fewer days. After an initial phase of correct use, a reduction in patient compliance was gradually reported in the first protocol. However, patient compliance in the second protocol remained high (96.25%) in the recording of all the required parameters. The Sm@rtEven application has proven to be a valuable tool for following patients remotely, especially during the pandemic. Telemedicine has the same value as traditional clinical evaluations, and it enables patients to be followed over long distances and over time, minimizing any discomfort.

No abstract

No abstract