ABSTRACT
Forecasting is of utmost importance for the Tourism Industry. The development of models to predict visitation demand to specific places is essential to formulate adequate tourism development plans and policies. Yet, only a handful of models deal with the hard problem of fine-grained (per attraction) tourism demand prediction. In this paper, we argue that three key requirements of this type of application should be fulfilled: (i) recency-forecasting models should consider the impact of recent events (e.g. weather change, epidemics and pandemics); (ii) seasonality-tourism behavior is inherently seasonal; and (iii) model specialization-individual attractions may have very specific idiosyncratic patterns of visitations that should be taken into account. These three key requirements should be considered explicitly and in conjunction to advance the state-of-the-art in tourism prediction models. In our experiments, considering a rich set of indoor and outdoor attractions with environmental and social data, the explicit incorporation of such requirements as features into the models improved the rate of highly accurate predictions by more than 320% when compared to the current state-of-the-art in the field. Moreover, they also help to solve very difficult prediction cases, previously poorly solved by the current models. We also investigate the performance of the models in the (simulated) scenarios in which it is impossible to fulfill all three requirements-for instance, when there is not enough historical data for an attraction to capture seasonality. All in all, the main contributions of this paper are the proposal and evaluation of a new information architecture for fine-grained tourism demand prediction models as well as a quantification of the impact of each of the three aforementioned factors on the accuracy of the learned models. Our results have both theoretical and practical implications towards solving important touristic business demands.
Subject(s)
Policy , TourismABSTRACT
This paper aims to introduce our publicly available datasets in the area of tourism demand prediction for future experiments and comparisons. Most of the previous works in the area of tourism demand forecasting are based on coarse-grained analysis (level of countries or regions) and there are very few works and consequently datasets available for fine-grained tourism analysis (level of attractions and points of interest). In this article, we present our fine-grained enriched datasets for two types of attractions - (I) indoor attractions (27 Museums and Galleries in U.K.) and (II) outdoor attractions (76 U.S. National Parks) enriched with official number of visits, social media reviews and environmental data for each of them. In addition, the complete analysis of prediction results, methodology and exploited models, features' performance analysis, anomalies, etc, are available in our original paper, "Fine-grained tourism prediction: Impact of social and environmental features"[2].
ABSTRACT
INTRODUCTION: Histologic examination of teeth after regenerative endodontic treatment (RET) shows that the type, quality, and quantity of tissues formed in the root canal space are not predictable. The aim of this study was to examine clinically, radiographically, and histologically the outcome of RET in immature noninfected human teeth using SynOss Putty (Collagen Matrix Inc, Oakland, NJ) as a scaffold. METHODS: Three pairs of maxillary/mandibular first premolars in 3 patients scheduled for extraction were included. Sensibility tests confirmed the presence of vital pulps. After informed consent, anesthesia, and rubber dam isolation, the pulps were removed. RET was performed using the following scaffolds: SynOss Putty + blood in both teeth in patient #1, SynOss Putty with or without blood in patient #2, and SynOss Putty + blood or blood only in patient #3. After a follow-up period of 2.5-7.5 months, the teeth were clinically and radiographically evaluated, extracted, and examined histologically. RESULTS: Patients remained asymptomatic after treatment. Radiographic examination of the teeth showed signs of root development after treatment. In teeth treated with SynOss Putty + blood, histologic examination showed formation of intracanal mineralized tissue around the scaffold particles solidifying with newly formed cementumlike tissue on the dentinal walls. The tooth treated with SynOss Putty without blood showed the formation of a periapical lesion. The tooth treated with a blood clot only showed tissues of periodontal origin growing into the root canal space. CONCLUSIONS: SynOss Putty + blood showed a predictable pattern of tissue formation and mineralization when used as a scaffold for RET in human immature noninfected teeth. The newly formed mineralized tissue solidifies with newly formed cementum on the dentinal walls.
