Forecasting Future Living Costs in Cities – Digital Artefact
Duran and Puga (2013) elucidate four key drivers underpinning the population surge in cities within developed economies: transportation and housing supply, amenities, agglomeration effects, and technological advancements. These factors collectively fuel urban growth, inevitably leading to escalated living costs. The exponential rise in demand, driven by population expansion, further exacerbates these costs, creating a significant challenge for residents and policymakers alike. However, despite the wealth of data and technological advancements at our disposal, there is currently no technology capable of furnishing a predictive cost model for cities. Consequently, the question arises: can we foresee the future living costs of a city with the available information on costs? By analysing this data, can policymakers identify areas where residents face disproportionate financial burdens and prioritise interventions to alleviate these disparities?
This video explores the complex dynamics driving the growth of cities in developed economies and the consequent rise in living costs. One of the primary challenges explored in the video is the difficulty of accurately predicting future living costs. Despite advancements in data analytics and access to vast information, no technology currently provides a precise predictive cost model for cities. However, the video concludes on an optimistic note, suggesting that with the present information and advancements in predictive analytics, there may be potential avenues to explore for forecasting future living costs. It encourages further research and exploration into innovative approaches such as Big Data and IoT that could revolutionise urban cost prediction.
Executive Summary
The United Nations (UN) estimated in the most recent 2019 update of the World Population Prospects (WPP) that the global population will grow by 2 billion over the next 30 years, reaching 9.7 billion by 2050 and 10.9 billion in 2100 (United Nations, 2019). Income inequality within countries has increased, and despite progress in reducing poverty, there is a growing consensus on the necessity for inclusive development that encompasses economic, social, and environmental dimensions (Teh & Rana, 2023; Dourado & Montini, 2016). The world increasingly demands attention to demographic changes and innovative housing solutions. Livable cities and living costs are consistently top subjects in the media and among various governments. (Cheng et al. 2021, Dourado & Montini 2016). In our highly globalised yet increasingly concentrated urban food supply system, reducing inequality within and among countries is closely linked to addressing disparities within the food system itself. Food provides a valuable lens for revealing and addressing the various layers of inequality in industrialised countries and their supply chains. (Illieva 2017). Besides the strategies already mentioned for managing unequal food access, there are further inequalities at the state and federal levels in urban food policy-making.
The Role of Big Data in Addressing Inequality
Big Data technology has already transformed various sectors, such as business and financial services, through GPS, Bluetooth, and online shopping applications (Teh & Rana 2023). It has the potential to revolutionise statistical systems by:
- Entirely or partially replacing existing statistical sources
- Providing complementary or new statistical information
- Improving estimates from current statistical sources
In the context of SDG 10, which is to reduce inequality within and among countries, big data can be instrumental in understanding and mitigating economic disparities. For example, data regarding government funds allocated to local food and agriculture businesses can be analysed to ensure equitable distribution, thereby supporting inclusive policies. This meets target indicator 10.5, which aims to “improve the regulation and monitoring of global financial markets and institutions and strengthen the implementation of such regulations” (United Nations, 2023). Philadelphia’s food system plan illustrates this measure, where Big Data can form equitable funding strategies between commodity and non-commodity produce, addressing economic inequalities in the food supply system.
Big data develops a better understanding of inequalities in upward mobility to inform policies regarding tax, housing, education, etc. Still, it is only divulged when data is available to the consumer. Big data can detect economic fluctuations, such as interest rates affecting families struggling with the cost of living crisis. With the help of big data, People can predict and prepare for economic upheaval. Therefore, data availability can answer SDG 10 with a design to support those with disadvantaged backgrounds.
Urban Food Systems Strategies Targeting SDGs
Philadelphia’s food system plan offers an illustrative blueprint for how Big Data can revolutionise current statistical systems. The plan (DVRPC 2011) identifies ten indicators (land in production, profitability of farming, surface water quality, farmland preservation, employment in the food system, food and farmworker wages, healthy food purchases, health of residents, affordability of nutritious food and food insecurity) that can illustrate past and ongoing changes to regional, national, and global food systems, illuminate trends in food systems, and help hypothesise what other changes or interventions are needed to shift indicators. To achieve greater equality within and between countries (SDG 10), policy interventions (target 10.4) should consider how government funds are allocated to local food and agriculture businesses (Illieva 2017). This includes distinguishing between commodity and non-commodity payments, as Philadelphia’s food system plan recommends.
IoT and Smart Solutions
The Internet of Things (IoT) facilitates the creation of smart cities through advanced technologies that transform urban living (Teh & Rana 2023) Smart solutions to answer SDG 12 are well implemented, but greater attention is needed to answer SDG 10. For instance, integrating mobile phone data can provide granular insights into the socio-economic status of populations, enabling targeted assistance to the bottom 40% of the population and promoting income growth as outlined in SDH targets 10.1 and 10.2.
Leveraging Mobile Phone Data to Assess Socio-Economic Status for Achieving SDG Targets
Target 10.1 of the Sustainable Development Goals (SDGs) aims to achieve and sustain income growth of the bottom 40% of the population at a rate higher than the national average by 2030. This target is measured using the growth rates of household expenditure or income per capita among the bottom 40% of the population and the total population. While traditional data sources have limitations in providing timely and detailed insights, mobile phone data presents a novel solution for assessing the socioeconomic status of populations at granular levels (Bok et al. 2018; Lokanathan et al. 2017). Thereby contributing towards identifying the bottom 40% and enabling targeted assistance to promote income growth.
Mobile phone data, encompassing call detail records (CDRs), geolocation data, and usage patterns, offers a rich and continuous stream of information that can be leveraged to infer various socio-economic indicators (Erlström et al. 2022; Lokanathan et al. 2017). Key advantages of investigating this data include granularity and timeliness, widespread coverage, and behavioural insights (Elmassah & Mohieldin 2020). Mobile phone data can provide real-time and location-specific insights, allowing for timely interventions. With high penetration rates of mobile phones, even in developing countries, this data source covers diverse population segments, including those often missed by traditional surveys. Calling patterns, mobility, and data usage can reveal behavioural trends indicative of socioeconomic statuses, such as employment stability, social interaction, and access to services (Erlström et al., 2022). Big Data analytics can, therefore, detect economic fluctuations and predict financial risks, aiding in preparation for economic upheaval. This predictive capability is crucial for designing support systems for disadvantaged backgrounds, aligning with SDG 10’s objectives. By providing a deeper understanding of inequalities in upward mobility, Big Data can inform policies on taxation, housing and education, ensuring they are inclusive and equitable.
Implementation for Target 10.1
Several vital steps must be implemented to utilise mobile phone data effectively to achieve Target 10.1 of the Sustainable Development Goals. Firstly, collaboration with mobile network operators is essential to access anonymised and aggregated mobile phone data. This data should then be integrated with existing socio-economic datasets for comprehensive analysis. Developing machine learning models is crucial for classifying and predicting socio-economic status based on mobile phone usage patterns. To ensure accuracy and reliability, these models must be rigorously trained and validated using labelled data from households surveyed or other verified sources. Establishing a continuous monitoring system is also vital for tracking changes in socioeconomic status over time. Such a system can provide early warnings of economic distress and help identify areas that require targeted interventions. Finally, the insights derived from mobile phone data should be used to inform the design and implementation of targeted assistance programs. These programs should focus on regions with high concentrations of the bottom 40% of the population, ensuring that resources are directed where they are most needed; this systematic approach can significantly enhance the efficacy of efforts to promote income growth and economic inclusion, thereby contributing to the achievement of Target 10.1.
Conclusion
Integrating Big Data and IoT holds significant promise in addressing SDG 10 by providing the tools necessary to design and implement targeted assistance programs. Economic geolocation data can be suspended and utilised using geolocation data from mobile phone usage. Calling patterns, mobility, and data usage can reveal behavioural trends indicative of socioeconomic status. While the potential benefits are substantial, navigating the associated risks and challenges is imperative. Through continued research and careful implementation, these technologies can contribute to a more inclusive and equitable world, addressing the multifaceted dimensions of inequality in an increasingly urbanised and interconnected global landscape.
Bibliography
Bok, B, Caratelli, D, Giannone, D, Sbordone, A & Tambalotti, A 2018, ‘Macroeconomic Nowcasting and Forecasting with Big Data’, Annual Review of Economics, Vol.10, No.1, pp. 615-643.
https://doi.org/10.1146/annurev-economics-080217-053214
Cheng, X, Liu, S, Sun, X, Wang, Z, Zhou, H, Shao, Y & Shen, H 2021, ‘Combating emerging financial risks in the big data era: A perspective review’, Fundamental Research, Vol 1, No.5, pp.595-606.
https://doi.org/10.1016/j.fmre.2021.08.017’
Dourado, R, Montini, A 2016, ‘The cost of living in the best livable cities in the word: a brief predictive quantitative analysis’, International Journal of Multivariate Data Analysis, Vol 1., No.1, pp. 28-42.
https://doi.org/10.1504/IJMDA.2016.081078
Duranton, G, Puga, D 2013, ‘The Growth of Cities’, CEPR Discussion Paper, No. DP9590.
DVRPC 2011, ‘Eating Here: Greater Philadelphia’s Food System Plan’
Available at: https://www.dvrpc.org/products/10063
Elmassah, S, Mohieldin, M 2020, ‘Digital transformation and localising the Sustainable Development Goals (SDGs)’, Ecological Economics, Vol 169. Pp. 1-3.
https://doi.org/10.1016/j.ecolecon.2019.106490.
Erlström, A, Grillitsch, M & Hall, O 2022, ‘The geography of connectivity: a review of mobile positioning data for economic geography’, Journal of Geographical Systems, Vol 24., No. 3.
Illieva, R 2017, ‘Urban Food Systems Strategies: A Promising Tool for Implementing the SDGs in Practice’, Sustainability, Vol 9., No. 10.
https://doi.org/10.3390/su9101707
Lokanathan, S, Gomez, T & Zuhyle, S 2017, ‘Mapping Big Data Solutions for the Sustainable Development Goals [Draft]’, LIRNasia, Canada, p.30.
Teh, D, Rana, T 2023, ‘The Use of Internet of Things, Big Data Analytics and Artificial Intelligence for Attaining UN’s SDGs’, Handbook of Big Data and Analytics in Accounting and Auditing, p.235-253.
https://doi.org/10.1007/978-981-19-4460-4_11
United Nations 2019, ‘World Population Prospects 2019: Highlights’, Department of Economic and Social Affairs.
United Nations 2023, ‘Goal 10’, Department of Economic and social Affairs.
