Hotel booking cancellation prediction is crucial in conducting revenue and resource management for hotels. This paper provides three possible substitutes for the neural network including logistic regression, k-Nearest Neighbor (k-NN), and CatBoost, whereas CatBoost, is the most suitable model for hotels to do the prediction. The advantages of them are effectiveness, high accuracy, and lower cost. The dataset used in this paper was adapted from Kaggle, a set of the booking data from two types of hotels (resort hotel and city hotel) in Portugal, and the corresponding customers' information. We select some key variables as the predictor to train and test the prediction models based on three machine learning algorithms. After preprocessing the raw data, i.e., standardizing, dealing with missing data, recoding some variables, and scaling, we conduct the prediction and compare each model through three metrics (confusion matrix, accuracy score, and 1 F -score). The result indicates that CatBoost has the best performance in predicting hotel booking cancellation because it has the greatest number of correct prediction samples and the highest accuracy score. We focus on the efficiency and economy of doing cancellation prediction in the hospitality industry to form a basis for future revenue and resource management for hotels.

No abstract

BackgroundChanges in the neutrophil-lymphocyte ratio (NLR) has been reported to be associated with epilepsy. Here we aim to investigate the correlation of temporal changes of NLR level with seizure severity and the follow-up seizure attacks in patients with epilepsy (PWE).MethodsWe performed a retrospective analysis of the laboratory data including leukocyte count and NLR within 24 h of acute seizure and during the follow-up period of 5–14 days after acute seizure (NLR1, NLR2, respectively) in 115 PWE, and 98 healthy individuals were included as controls in this study. The correlation of laboratory data with seizure types, etiology of epilepsy, anti-seizure drugs (ASDs), seizure severity, and the follow-up seizure attacks in PWE was studied.ResultsLeukocyte count (P < 0.001) and NLR level (P < 0.001) were found significantly different between PWE and controls. On the other hand, a multivariable logistic regression analysis showed that NLR1 level (OR = 2.992, P = 0.001) and admission leukocyte (OR = 2.307, P = 0.002) were both independently associated with acute epileptic seizures. Especially, higher NLR1 level was significantly associated with status epileptics (P = 0.013) and recurrent seizures after admission (P < 0.001). Furthermore, the multivariable logistic regression analysis indicated that higher NLR1 was a predictor for the tendency of the following recurrent seizure attacks (OR = 1.144, P = 0.002). NLR2 was inversely correlated with ASDs taken (P = 0.011). Levels of NLR1 (r = 0.441, P < 0.001) and NLR2 (r = 0.241, P = 0.009) were both positively correlated with seizure severity.ConclusionsSeizures were correlated with the alterations of systemic inflammation reflected by leukocyte and NLR. NLR1 and admission leukocyte were both independently associated with acute epileptic seizures. Higher NLR1 was associated with status epilepticus and independently predicted the tendency of the following epileptic seizures. NLR2 was significantly associated with ASDs taken. Besides, NLR may be used as a biomarker for seizure severity.

Anti-leucine-rich glioma-inactivated1 (Anti-LGI1) autoimmune encephalitis is a rare autoimmune disease discovered in recent years. It is generally not defined as an inherited disease, though its etiology is still unclear. Herein, we report the first case of adult patients with familial anti-LGI1 encephalitis. Two biological siblings who worked in different regions were successively diagnosed with anti-LGI1 encephalitis in their middle age. The two patients had similar clinical manifestations including imaging results. Their clinical symptoms improved after immunotherapy and antiepileptic therapy. Given that some unique human leukocyte antigen (HLA) subtypes appear at a high frequency, multiple recent studies have revealed that anti-LGI1 encephalitis is associated with genetic susceptibility. One of the patients underwent HLA genotyping and whole-exome sequencing (WES), revealing the same HLA typing as in previous studies and two rare HLA variants. Therefore, further studies involving larger samples and more populations should be conducted to explore the possibility of other influencing factors such as environmental impacts.