Explore the vast range of titles available.

PurposeThe aim of the paper is to test and demonstrate the potential benefits in applying reinforcement learning instead of traditional methods to optimize the content of a company's mobile application to best help travellers finding their ideal flights. To this end, two approaches were considered and compared via simulation: standard randomized experiments or A/B testing and multi-armed bandits.Design/methodology/approachThe simulation of the two approaches to optimize the content of its mobile application and, consequently, increase flights conversions is illustrated as applied by Skyscanner, using R software.FindingsThe first results are about the comparison between the two approaches – A/B testing and multi-armed bandits – to identify the best one to achieve better results for the company. The second one is to gain experiences and suggestion in the application of the two approaches useful for other industries/companies.Research limitations/implicationsThe case study demonstrated, via simulation, the potential benefits to apply the reinforcement learning in a company. Finally, the multi-armed bandit was implemented in the company, but the period of the available data was limited, and due to its strategic relevance, the company cannot show all the findings.Practical implicationsThe right algorithm can change according to the situation and industry but would bring great benefits to the company's ability to surface content that is more relevant to users and help improving the experience for travellers. The study shows how to manage complexity and data to achieve good results.Originality/valueThe paper describes the approach used by an European leading company operating in the travel sector in understanding how to adapt reinforcement learning to its strategic goals. It presents a real case study and the simulation of the application of A/B testing and multi-armed bandit in Skyscanner; moreover, it highlights practical suggestion useful to other companies.

Violence and armed conflicts have emerged as prominent factors driving food crises. However, the extent of their impact remains largely unexplored. This paper provides an in-depth analysis of the impact of violent conflicts on food security in Africa. We performed a comprehensive correlation analysis using data from the Famine Early Warning Systems Network (FEWSNET) and the Armed Conflict Location Event Data (ACLED). Our results show that using conflict data to train machine learning models leads to a 1.5% increase in accuracy compared to models that do not incorporate conflict-related information. The key contribution of this study is the quantitative analysis of the impact of conflicts on food security predictions.

Reports from the Famine Early Warning Systems Network (FEWSNET) serve as the benchmark for food security predictions which is crucial for stakeholders in planning interventions and support people in need. This paper assesses the predictive accuracy of FEWSNET's food security forecasting, by comparing predictions to the following ground truth assessments at the administrative boundaries-livelihood level, revealing an overall high accuracy of 78\\% across diverse timeframes and locations. However, our analysis also shows significant variations in performance across distinct regions and prediction periods. Therefore, our analysis sheds light on strengths, weaknesses, and areas for improvement in the context of food security predictions. The insights derived from this study not only enhance our understanding of FEWSNET's capabilities but also emphasize the importance of continuous refinement in forecasting methodologies.

Abstract Background Anemia is a common extraintestinal manifestation of inflammatory bowel disease (IBD), with a 6% to 74% prevalence and a negative impact on patient survival and quality of life, although the prevalence is apparently declining due to improved disease treatment. We aimed to investigate the prevalence, pathogenesis, and clinical correlates of anemia in Italian patients with IBD. Methods A multicenter, prospective, observational study, involving 28 Italian gastroenterology centers, was conducted to investigate the epidemiology and consequences of IBD-associated anemia. Clinical and laboratory data of anemic patients were obtained at study enrolment. Results Anemia was diagnosed in 737 of 5416 adult IBD outpatients (prevalence 13.6%); females were more commonly affected than males (odds ratio, 1.5; 95% confidence interval [CI], 1.2–1.7) and had more severe anemia. In the majority of cases, anemia was due to iron deficiency (62.5% of cases; 95% CI, 58.3%–66.6%), either isolated or in association with inflammation and/or vitamin deficiencies; anemia of inflammation accounted for only 8.3% of cases. More severe anemia was associated with increasing fatigue and worse quality of life. Only 68.9% of anemic patients with iron deficiency (95% CI, 63.4%–73.8%) and 34.6% of those with vitamin deficiencies (95% CI, 26.2%–44.2%) were properly treated with supplementation therapy. Conclusions In Italy, the prevalence of IBD-associated anemia is lower than previously reported. Anemia of IBD is most commonly due to iron deficiency and contributes to fatigue and poor quality of life, but remains untreated in a large proportion of patients with iron and/or vitamin deficiencies. This study is registered at clinicaltrials.gov as NCT02872376. Lay Summary The prevalence of inflammatory bowel disease–associated anemia is 13.6%. The prevalence is higher among females younger than 50. Anemia is usually due to iron deficiency and adversely affects fatigue and quality of life. Many patients with iron or vitamin deficiency (31% and 65%, respectively) remain untreated.

Recent legislation concerning air pollutant emissions from ships (Tier III) has considerably decreased NOx emission limits for recreational ships with less than 500 gross tonnages and greater than 24 m load line length (LLL), the so-called “large yachts”. For these yachts, which adopt multiple Diesel engines with maximum power ranging from 800 to 2000 kW, the new NOx limit is less than 2 g/kWh. To satisfy that limit, engine makers suggest the adoption of a classic SCR system with urea injection but this methodology, in addition to requiring a large space for installation, does not seem so appropriate for diesel engines of large yachts that normally operate at low power with exhaust temperatures often well below 300 °C, therefore not sufficient to allow the correct functioning of the SCR. The aforementioned circumstances have prompted Sanlorenzo Spa (La Spezia – Italy), one of the world’s leading companies in the production of pleasure boats, to collaborate with the University of Pisa in the study of alternative solutions to SCR systems. Recently there is a great interest in innovative NOx abatement systems, based on the possibility of absorbing NOx molecules into seawater through the utilization of appropriate aqueous solutions containing targeted saline oxidizing agents. The present study describes the first results of a research program aimed to identify, from one side, the best saline oxidizing agent for an aqueous NOx abatement and, from the other, the best washing methodology compatible with the propulsion layouts usually adopted on yachts. In the engine testing laboratories of the Department of Energy, Systems, Territory and Construction Engineering (DESTeC) of the University of Pisa, an experimental apparatus has been created to reproduce the real conditions of underwater engine exhausting. This device was combined with a small 1.2 L direct injection diesel engine. The first results showed a reduction of the NOx emissions of about 27% by using a gas washing with wet scrubber, followed by bubbling in water, using 0.2 molar NaClO saline solutions.

Background Both macroscopic and histological lesions are frequently detected at upper endoscopy in elderly patients. We assessed the prevalence of main endoscopic and histological alterations in elderly (> 65 years old) patients. Methods In this study, clinical, endoscopic and histological features of patients referred for upper endoscopy in clinical practice were retrieved. Both univariate and multivariate analyses were executed. Comparisons with previous data were performed. Results A total of 1336 underwent upper endoscopy in the 28 participating centres. At endoscopy, at least one macroscopic lesion was present in overall 420 (31.4%) patients. Erosive gastritis (13.3%) and erosive oesophagitis (9.8%) were the most prevalent lesions, whilst Barrett’s oesophagus, gastric ulcer, duodenal ulcer and erosive duodenitis were observed in 1.8%, 2%, 1.4% and 3.1% patients, respectively. Nine (0.6%) cases of oesophageal, 25 (1.8%) gastric and 2 (0.1%) duodenal neoplasia were detected. At histology, Helicobacter pylori infection was diagnosed in 99 (15.9%) patients, and extensive precancerous lesions on gastric mucosa were detected in 80 (14.5%) patients. Endoscopic lesions were more frequent in males, at first endoscopy and in those with alarm symptoms and lower during PPI therapy. At multivariate analysis, PPI therapy significantly reduced the probability of finding endoscopic lesions (OR: 0.68, 95% CI: 0.46–0.99; P  = 0.04), whilst neoplastic lesions were associated with presence of alarm symptoms (OR: 1.5, 95% CI: 1.1–2.1; P  = 0.005). Conclusions We found that the frequency of erosive and neoplastic lesions remained high in elderly patients, whilst the prevalence of both H. pylori infection and peptic ulcer was decreased.