Anesu Jahura was the winner of the ITS UK 2023 Early Careers Competition, for the best essay in the student or apprentice category. Here, you can read his winning essay. Find out more about the competition here.

Introduction

Data has taken the world by storm. Advancements in areas such as machine learning, big data, and computer vision have led to a “data revolution” which has transformed entire industries and enhanced productivity, and even influenced the way we entertain ourselves. The data revolution has changed the world in many ways, and transport services have been no exception.

Data is information that is collected about people, places, or events in reality and is eventually stored in a file or database. There are two general types of data that exist: qualitative and quantitative. Qualitative data involves non-numerical information that is usually categorical in nature and thus helps businesses make informed decisions. Quantitative data is usually numerical and is often used for quantitative decision-making such as budget planning. Not all data is useful, however, and as the amount of data available rises daily, it is becoming increasingly important to analyse datasets carefully to determine which data provides useful insights and which data is uninformative.

How Data Can be Used in Transport Industries

Overview

Data helps to enhance the effectiveness and efficiency of transport services. The benefit of using transport data is that it empowers transport professionals to make informed decisions using current and historical information, and global positioning system (GPS) technology encapsulates this. Originally developed for military purposes [2], the tracking and positioning capabilities of GPS technology have had a strong impact on transportation industries worldwide, as users are able to navigate trips using real-time travel data to determine the optimal routes to reach their destinations. This technology is now widely accessible, enabling private, public and commercial transport users alike to take advantage of the operational benefits.

The advantages of using data in transport services go far beyond GPS capabilities and route optimisation. In many of the world’s transport industries, information technology (IT) systems supported by data provide many advantages when it comes to planning, implementing, and using transport services. These systems contribute to improvements such as increased safety and security, positive environmental impact and improved customer services. Figure 1 summarises the advantages of using data-supported IT systems in the transport industry. Each of these advantages are made possible by specific measures and technologies.

Commercial Transport

Data for modern commercial transport is often large and complex due to increased globalisation and digitisation. Thus, the ability to process large datasets (i.e., big data analytics) is key for commercial transport operators. Operational efficiency is crucial in commercial transport, and using automated data processing usually provides superior decision-making capabilities, better process quality, and optimal resource optimisation. For example, anticipatory shipping uses automated data processing to predict demand for future orders and ship them in advance, reducing delivery lead times and improving customer satisfaction. Figure 2 illustrates an anticipatory shipping method patented by Amazon in 2013, which helped the company improve the efficiency of its outbound logistics. The retail giant has since made use of anticipatory shipping through advanced demand forecasting methods powered by artificial intelligence (AI), which enabled it to guarantee 2-day shipping lead times for its premium customers.

Another useful application of automated data processing is in fleet applications. Vehicle fleet management can be performed from central monitoring stations, which enables commercial transport operators to monitor the positions of multiple vehicles continuously and provide other useful technical feedback automatically as their vehicles traverse. This makes it easier to manage fleets. The scope of automated data processing for fleet management extends beyond commercial transport and logistics, as law enforcement agencies, emergency services and other public or government services can also utilise automated data processing to enhance their fleet management capabilities.

Commercial transport companies must continue to adopt innovative, future-focused technologies to thrive in the modern economy, and the strategic use of insightful data is key in this regard.

Public Transport

An effective and efficient public transport system is vital for the economy of any country, as it enables the mobility of its citizens to seek economic opportunities. A pertinent example of the use of data to manage public transport is Transport for London (TfL), which oversees the public transport network in London. Considering that London is the largest city in the United Kingdom with approximately 8.9 million people, TfL has to process, manage, and analyse large amounts of transport data to run the city’s public transport networks.

TfL mainly uses big data analytics to map customer journeys, manage unexpected events, and provide personal travel information to commuters. This has enhanced the travel experiences of commuters in London. This progress can be built upon further to refine the public transport network according to commuters’ needs as more data is collected and better insights are drawn.

Data is essential not only for public transport networks in developed regions like the United Kingdom, but also for developing countries where less structured forms of public transport exist.

In South Africa – one of Africa’s more established developing economies – only 30.6% of households own a vehicle [10], leaving the rest of the population to rely on alternative forms of transport like walking and public transport. Minibus taxi travel is by far the most popular form of transport in the country, with approximately 62% of households relying on minibus taxis as their main mode of transport [11]. Unlike private taxis operating in more developed countries, these minibus taxis operate informally with demand-driven operations that are difficult for authorities to regulate.

Public transport services in South Africa can be improved through policies for formalising the minibus taxi industry, proper trip scheduling, and the integration of modern technologies such as the electrification of minibus taxis. This will require the collection and analysis of different types of data from multiple sources such as passenger demand data and environmental impact data, presenting an opportunity for multidisciplinary efforts to transform the country’s transport industry using data.

Private Transport

Data-centred private transport strategies focus on using data to enhance personal travel. Established innovations like GPS technology have increased the quality of private transport. Service-oriented approaches such as ride-hailing platforms as well as ride-sharing and carpooling services have also increased accessibility to affordable and personalised private transport.

Mobility as a service (MaaS) is a key data-centred innovation that has changed the landscape of transport services in some cities. With MaaS, citizens can receive transport services from multiple providers through a centralized interface, enabling them to search, find, and book trips in one place . Naturally this requires the collection and processing of large amounts of data, but cities like Helsinki in Finland have shown this is possible. Whim is the “all-in-one” mobile application that residents in Helsinki can use to access numerous modes of transportation including public transport, bikes and e-scooters, and even rental cars and shared rides. This user-centred technology has made it easier for Helsinki residents to live without owning their own vehicles, providing a promising example of how the number of vehicles on roads globally can be reduced. In addition to having positive environmental effects from the resulting carbon reduction, this would decrease congestion and visual pollution.

More radical technologies have also been on the rise in the transportation industry. As the global population increases along with the number of people driving private vehicles, there is a need for safer, more ergonomic transport. Automated driving technology is one of the technologies leading the front in this regard. The level of automation in vehicles ranges from level 0 with no automation (i.e., completely unassisted) to level 5 with full automation. Higher levels of automation utilise real-time and historic traffic, geographic and infrastructure data to inform decision-making, along with sensors to perceive environmental conditions and to communicate with infrastructure and other vehicles on the road. Figure 3 illustrates the basic architecture for automated vehicles and describes the complete process from data acquisition to decision-making and actuation.

Conclusion

The data revolution has influenced many industries globally, including transportation services. The collection, processing and analysis of relevant transport data can help to increase the effectiveness and efficiency of transport services through informed decision-making and innovation.

Commercial transport companies utilise data to improve their operations though forward-thinking measures such as anticipatory shipping and automated fleet management processes. Public transport systems can also benefit from data-centred transport management to provide better offerings and enhance commuters’ travel experiences. Developing economies can use data as a catalyst to transform their transport systems to suit modern mobility needs. Innovations like GPS technology and ride-hailing platforms have increased the affordability and accessibility of private transport, and advancements such as MaaS offerings show promise in revolutionising transport systems globally by reducing the reliance on owning private vehicles.

Transport professionals and researchers should look to further improve on current data-centred developments in transport technology and embrace modern innovations to continue providing high-quality transport services. The focus should be on extracting useful insights from relevant data to maximise the accessibility, affordability and sustainability of transport services.

References

1] Kendall, K.E & Kendall, J.E. 2020. Systems Analysis and Design. 10th Edition. Pearson Education Limited.

[2] Mintsis, G., Basbas, S., Papaioannou, P., Taxiltaris, C & Taxiltaris, I.N. 2004. Applications of GPS technology in the land transportation system. European Journal of Operational Research. Vol. 152, Issue 2. https://doi.org/10.1016/S0377-2217(03)00032-8.

[3] Kartsan, P., Kartsan, I., Zhukov, A. & Klementeva, M. The revolution of IT technologies in the transport economy: application and essence. E3S Web of Conferences. Vol. 471. http://dx.doi.org/10.1051/e3sconf/202447106003.

[4] Borgi, T., Zoghlami, N. & Abed, M. Big data for transport and logistics: A review. 2017. International Conference on Advanced Systems and Electric Technologies. https://doi.org/10.1109/ASET.2017.7983742.

[5] Selyukh, A. 2018. Optimized Prime: How AI And Anticipation Power Amazon’s 1-Hour Deliveries. NPR. Available at: https://www.npr.org/2018/11/21/660168325/optimized-prime-how-ai-and-anticipation-power-amazons-1-hour-deliveries (Accessed 21 January 2024).

[6] Spiegel, J.R, McKenna, M.T., Lakshman, G.S. & and Nordstrom, P.G. 2013. Method and system for anticipatory package shipping. US-8615473-B2.

[7] Thong, S.T.S., Han, C.T. & Rahman, T.A. 2007. Intelligent Fleet Management System with Concurrent GPS & GSM Real-Time Positioning Technology. 7th International Conference on ITS Telecommunications. https://doi.org/10.1109/ITST.2007.4295849.

[8] Trust for London. n.d. London’s geography and population. Available at: https://trustforlondon.org.uk/data/geography-population/ (Accessed 23 January 2024).

[9] Marr, B. 2016. Big Data in Practice: How 45 Successful Companies Used Big Data Analytics to Deliver Extraordinary Results. Wiley.

[10] de Villiers, J. Almost a third of South African households now own their own cars – while 90% have electric stoves. Available at: https://www.news24.com/bi-archive/general-household-survey-2018-south-african-households-third-own-cars-electrical-stoves-2019-5 (Accessed 24 January 2024).

[11] Statistics South Africa. National Households Travel Survey 2020. Pretoria. Available at: https://www.statssa.gov.za/publications/P0320/P03202020.pdf#page=114. (Accessed 25 January 2024).

[12] Smith, G. & Hensher, D.A. 2020. Towards a framework for Mobility-as-a-Service policies. Transport Policy. Vol. 89. https://doi.org/10.1016/j.tranpol.2020.02.004.

[13] Deloitte. The rise of Mobility as a Service. Available at: https://www2.deloitte.com/nl/nl/pages/consumer-industrial-products/articles/the-rise-of-mobility-as-a-service.html (Accessed 25 January 2024).

[14] Offer, G.J. 2014. Automated vehicles and electrification of transport. Energy and Environmental Science. https://doi.org/10.1039/C4EE02229G.

[15] González, D., Pérez, J., Milanés, V. & Nashashibi, F. A Review of Motion Planning Techniques for Automated Vehicles. Vol. 17, No. 4. https://doi.org/https://doi.org/10.1109/TITS.2015.2498841.