This article is published in the Case Study category.
Big Data meteorological analytics may help in preventing natural hazards from becoming disasters and save lives. Data related to air temperature, precipitation, sunlight intensity or pollution levels, allow building tools for resilience while aiming at economic development. In Indonesia, where the economic impact of tourism is high, Pulse Indonesia and its Haze Gazer initiative have gathered meteorological data to inform decision-makers and develop strategies to cope with the haze and its repercussions.
Indeed, according to Weather Analytics, 33% of worldwide GDP is affected by the weather leading to strong needs for Big Data and weather prediction analytics in sectors such as agriculture, insurance or tourism. Pioneer in the field, IBM’s Weather Company, is an example of IBM’s strategy to shift its target market towards predictive analytics, offering actionable services, such as predictions for airline companies.
Weather and tourism economy have clear financial correlations. Brands and local businesses count on the sunshine to boost their ice-cream and cold beers sales, provided that tourists have previously decided to visit this particular destination. In her literature review, The Importance of Climate And Weather For Tourism, Susanne Becken highlights the influence of the weather in the choice of a touristic destination and the related successful operation of tourism businesses, allowing her to say that: “tourist destinations will benefit from understanding potential climatic changes in their area and how they might impact on their operations.“ (ibid, p.2).
While Koreans have become experts in weather predictions, notably since the last PyeongChang Winter Olympics, DFRC’s team, in Seoul, analysed the correlation between Crowd Analytics, temperature and weekdays versus weekends, on the famous Seoullo Bridge.
LBASense Crowd Analytics are based on anonymous detections of mobile phones retrieved for a particular time and location. Adding the temperature data to this analysis allowed us to see the correlation between the popularity of the bridge on certain days and the outside temperature.
Over the entire winter, the data analysis, from January to March 2018, showed that the temperature had an impact on the decision to have a walk on the touristic bridge. The results prove that people’s behaviour is different from weekends and weekdays, considering additional factors like work and free time as drivers in the decision-making process. On top of that, warmer temperatures seem to invite people on Seoullo Bridge, increasing the crowd of 50% on average (55% over weekends, 45% over weekdays).
Based on these results, predictions could be built in order to provide tourism businesses such as festival organisers with detailed weather/crowd predictions.
As part of EUROSTARS’ PrOFT project, correlations are being made between Crowd Analytics and other external sources of data (such as weather data, BLE, NFC, biometrics data…), allowing to develop a prediction engine for the tourism industry. Also, PrOFT’s partners are heading to the stage of finding out how weather affects customers’ and tourists’ buying patterns. The first version of an analysis platform is expected to be released by July 2018.
Led by the Korean R&D SME, KNL Information Systems, PrOFT’s consortium is composed of four other partners: DFRC (R&D SME), HES-SO Valais/Wallis – Institute of Tourism of University of Applied Sciences Western Switzerland (University), SWU / SMIACF Sookmyung Women’s University Industry Academic Cooperation Foundation (University) and Unisem Co., Ltd (Large Company).
Interested in knowing more about PrOFT? Contact us.
Copyright © 2022 DFRC
43 Science Park Road #01-11 Rm 8, Singapore 117408