This case study explores the Data and Decision Support Deputyship in Saudi Arabia, which serves as a tourism data hub to modernise the national system of tourism statistics. The initiative encompasses the integration of diverse data sources, including traditional ones like visitor border and household surveys, administrative data, mobile positioning data, point of sale data, and accommodation booking data, along with innovative data analytics tools such as machine learning and AI modelling. The new data sources serve to reinforce traditional ones, enhance the timeliness and granularity of tourism data, and fill existing data gaps. This initiative caters to government agencies, tourism boards, and businesses in the sector, offering granular information, real-time insights, demographic analysis, and trends for tailored marketing strategies, infrastructure development, and visitor services.
The Data and Decision Support Deputyship in Saudi Arabia
Abstract
Saudi Arabia, driven by its Vision 2030, is positioning tourism as an important element in economic diversification. To support this, the Ministry of Tourism established the Tourism Intelligence Centre, which was later elevated to an independent deputyship to deliver research, analytics and insights that enable data-driven decision making for the Saudi tourism sector. The Data and Decision Support Deputyship currently serves as a tourism data hub to modernise the national system of tourism statistics through the adoption of innovative data sources and analytical methods.
The drive to integrate new data sources in Saudi Arabia's tourism statistics arises from the need for more accurate, timely, and comprehensive information to facilitate informed decision-making in the tourism sector. The data guide strategic planning, economic assessments, market research, and decisions related to infrastructure, marketing, and resource allocation, contributing to sustainable growth, attracting investors, optimising tourism resource management, and fostering overall success and resilience in the tourism sector.
The initiative encompasses the integration of diverse data sources, including traditional ones like visitor border and household surveys, administrative data, mobile positioning data, point of sale data, and accommodation booking data, along with innovative data analytics tools such as machine learning and AI modelling. The new data sources serve to reinforce traditional ones, enhance the timeliness and granularity of tourism data, and fill existing data gaps. Furthermore, they enable more in-depth insights, such as measuring tourism flows at the sub-national level. This initiative caters to government agencies, tourism boards, and businesses in the sector, offering granular information, real-time insights, demographic analysis, and trends for tailored marketing strategies, infrastructure development, and visitor services. The developmental approach initially focuses on national-level data, gradually expanding to cover individual tourism destinations.
The initiative has reached a mature stage of implementation, with the establishment of data collection mechanisms and preliminary analyses conducted on foundational datasets. Future steps entail the expansion of access to various big data and administrative data sources, broadening geographical coverage, and refining the analytical models. The Ministry of Tourism initially intended to utilise mobile positioning data for measuring international tourism flows, both inbound and outbound, leveraging roaming services data. However, the implementation plan for mobile positioning data was affected by the COVID-19 pandemic, leading to a rescheduling of activities. Despite this impact, the initiative remains within the current year's plan and is scheduled for implementation. Furthermore, regular reviews and updates to the initiative's framework are scheduled to guarantee its sustained relevance and effectiveness.
Source: International Affairs Deputyship, Saudi Arabia
The initiative on utilising new data sources for tourism statistics in Saudi Arabia is an ongoing project and is positioned to be a significant data asset within the Ministry of Tourism. The governance structure emphasises collaboration among government bodies, private sector entities, and technology providers, all under the purview of the Ministry of Tourism. In alignment with this, the Ministry of Tourism adopted the National Data Governance Regulations developed by the Saudi Authority for Data and Artificial Intelligence. To facilitate effective governance of new tourism data sources and other aspects related to official tourism statistics, the Ministry of Tourism has established a dedicated Data Management Office integrated into the organisational structure of the Data and Decision Support Deputyship. This office plays a crucial role in safeguarding good governance practices and the secure management of the evolving data landscape in the tourism sector.
Mobile positioning data
The approach for utilising mobile positioning data for tourism statistics consists of three phases.
Phase 1: Domestic tourism flows
This phase concentrated on Domestic Tourism Flows Data and involved three sequential steps as shown in Figure 2. Firstly, the focus was on gathering data specifically related to overnight domestic visitors. Subsequently, the initiative expanded to encompass the collection of data on total visitors, considering both same-day and overnight stays. Finally, the third step involved collecting detailed information on the visited destinations, encompassing both main and secondary visits.
Source: International Affairs Deputyship, Saudi Arabia
Phase 2: Visits to tourist attractions
This phase involves the measurement of the precise number of visitors to specific locations that are deemed as points of interest for tourism development and attractions in Saudi Arabia. Such measurements are conducted through specifying each location polygon.
Phase 3: International tourism flows
This phase entails the collection of mobile positioning data for both inbound and outbound visitors based on the roaming services data. The implementation plan for this has been affected by the COVID-19 pandemic, leading to a rescheduling of activities.
The methodology for processing the raw mobile positioning data into results for domestic tourism visits and trips in Saudi Arabia is based on business rules that are set by the Tourism Intelligence Centre, and follows these steps:
Identification of home city. Each subscriber is assigned the main city where he/she has been present the most compared to other cities for each month. Based on a 6-month lookback window, the city topping in most months, or in case of several equal cities - the city with the latest month is defined as a home city for subscribers.
24-hour aggregation. For each domestic subscriber, the last location of each hour of the day is chosen from the raw signalling data to represent the unique location of that hour.
Assigning a city to each hour. For each last location of an hour, a city is assigned based on the cell and reference data.
Exclusion of non-tourism visits. Presence (visits) in home cities is excluded. Visits to the non-home cities closer than 80 km from the home city are marked, but not excluded (using cities distance matrix). Visits to non-home cities from home city that take place 4 or more times in a given month are also excluded.
Visit type. Visits with duration of more than 3 hours and less than 24 hours in the visited city are considered as same-day visits, visits longer than 24 hours are considered as overnight visits.
Trip calculation. Visits outside home city (not excluded in the previous part) are “combined” into trips. A trip is from home to back home. All consecutive visits which are not interrupted by a visit in home city comprise a single trip.
Main / secondary destination. Every trip is assigned one visit as the main destination. All other visits during the trip are identified as secondary destinations.
Results. Data are aggregated into breakdowns and indicators.
The methodology for processing international tourism flows through roaming services data will mirror the approach used for domestic mobile positioning data. The differentiation between visitors and non-visitors will be based on the country of residence and criteria specified in the International Recommendations for Tourism Statistics. The main focus of using mobile positioning data for inbound visitors is to refine primary and secondary destinations.
Point of sale data
Points of sale data provides an overview of visitors’ spend behaviour. The data are collected daily and shows the net volume of the transactions and net value spent on multiple tourism characteristic product categories (for example accommodation, shopping, travel agencies).
Domestic tourism: The total point of sale spend is filtered for tourism spend by domestic visitors in Saudi Arabia. Domestic tourism spending is classified as spending that is outside the visitor’s usual place of residence (their home city). This is defined as the city where the visitor made the largest number of transactions over a 12-month period. Due to high penetration of point of sale card usage among domestic population and the unified point of sale system, the data provides useful estimates of domestic spending and highly correlates with traditional data sources. However, due to some limitation in capturing specific transactions in destinations (such as online accommodation payments, domestic airlines, and fuel costs for land trips), traditional data sources are used to compute the final results after cross-checking and validating with point of sale data.
International tourism: Point of sale data are used to understand the characteristics of international visitors and create visitor segments based on the card issuing country, the season and time of visit, and the spending behaviour. Due to various challenges in using card transactions to measure tourism spending such as reliance on card use, under-coverage issues (including cash payments, prepayments, and online payments), partial coverage of spending items, and lack of coverage for aspects like purpose of visit and travel party composition, the point of sale data are primarily utilised to analyse trends and comparison figures. This approach provides greater granularity and reliability than if focusing on exact dollar values.
Accommodation data
As per the national tourism regulations, the licensed accommodation facilities are required to share booking details in real-time through the e-system “National Tourism Monitoring Platform”. The National Tourism Monitoring Platform is a major source for accommodation metrics such as occupancy rate, average daily rate, and other data. In addition to providing comprehensive historical reporting, the National Tourism Monitoring Platform provides future bookings that are used to forecast potential demand for accommodation services and tourism demand in general.
Machine learning and AI analytics models
A combination of the daily point-of-sale data and the monthly tourism demand survey data are used to forecast daily domestic tourism spending. To enhance the model's performance, significant variables such as the school vacations calendar, salary days, as well as Eid and Ramadan days were incorporated into the combined dataset. The application of a regression machine learning algorithm, specifically the XGBoost regression, proved to be the most effective and reliable for predicting daily domestic spending. Similarly, data from the National Tourism Monitoring Platform was used to predict weekly room occupancy and the average daily rate categorised by facility type (hotel, serviced apartment) across 15 destinations. Additional variables, including the Hijri calendar, school holidays, Eid and Ramadan days, and seasonal variations, were introduced to enhance prediction accuracy.
Improving tourism statistics is a national effort that requires close collaboration and co-ordination between different government entities to capture and share data efficiently and effectively to ensure timely, consistent, and comprehensive production of tourism statistics in line with international recommendations, while ensuring data privacy measures are implemented to protect the identities of visitors.
The initiative underscored the significance of diversifying data sources beyond conventional methods, emphasising the use of innovative channels such as mobile positioning data, point of sale, and administrative data to comprehensively understand tourism trends.
Lessons encompassed the adoption of advanced analytics tools, including machine learning and artificial intelligence, to process and interpret diverse datasets, thereby enhancing accuracy and efficiency in analysing non-traditional data. Strategic collaboration emerged as a crucial aspect, emphasising the necessity of forming partnerships between government bodies, private sector entities, and technology providers to access diverse data streams, technological expertise, and funding. The adoption of national data governance regulations reflected a commitment to structured and regulated data management, emphasising adherence to governance principles for the effective and responsible use of non-traditional data. Continuous evaluation and updates to the initiative's framework showcased a dedication to ongoing refinement, ensuring relevance and effectiveness.
Lessons included insights into the delicate balance between utilising non-traditional data for tourism insights and respecting privacy concerns, emphasising the critical importance of data security and privacy compliance. Clear communication with stakeholders, including the public, emerged as an essential strategy, with lessons focusing on transparently communicating the benefits of utilising non-traditional data sources and addressing concerns or misconceptions. In conclusion, the diversity of the tourism sector rejects the notion of a singular super data source. Acknowledging this, the emphasis should shift to integrating various data sources into a cohesive system.
It is essential to recognise that using new data sources for tourism is an ongoing project with several potential challenges to consider. One critical aspect is funding: it is crucial to secure funding for a minimum of three years. This is because the initial setup costs are higher than the ongoing operational costs, and the project typically takes at least three years to mature through pilots and trials. It is also essential to track lessons learned and potential improvements to the data and tools used to accelerate maturity and improve quality over time.
For further information please contact:
Faisal M. Al-Abdali, International Organizations Advanced Specialist, International Affairs Deputyship, anazifa@mt.gov.sa
This document, as well as any data and map included herein, are without prejudice to the status of or sovereignty over any territory, to the delimitation of international frontiers and boundaries and to the name of any territory, city or area.
© OECD 2025
Attribution 4.0 International (CC BY 4.0)
This work is made available under the Creative Commons Attribution 4.0 International licence. By using this work, you accept to be bound by the terms of this licence (https://creativecommons.org/licenses/by/4.0/).
Attribution – you must cite the work.
Translations – you must cite the original work, identify changes to the original and add the following text: In the event of any discrepancy between the original work and the translation, only the text of original work should be considered valid.
Adaptations – you must cite the original work and add the following text: This is an adaptation of an original work by the OECD. The opinions expressed and arguments employed in this adaptation should not be reported as representing the official views of the OECD or of its Member countries.
Third-party material – the licence does not apply to third-party material in the work. If using such material, you are responsible for obtaining permission from the third party and for any claims of infringement.
You must not use the OECD logo, visual identity or cover image without express permission or suggest the OECD endorses your use of the work.
Any dispute arising under this licence shall be settled by arbitration in accordance with the Permanent Court of Arbitration (PCA) Arbitration Rules 2012. The seat of arbitration shall be Paris (France). The number of arbitrators shall be one.
This document was produced with the financial support of the European Union. The views expressed herein can in no way be taken to reflect the official opinion of the European Union.