Mobile phone data statistics as a dynamic proxy indicator in assessing regional economic activity and human commuting patterns

 Introduction:

Phones are being utilized for a variety of purposes beyond texting. There is no way to track a landline phone's owner's whereabouts. Mobile phone habits may provide demographic and economic information. As a result, regional and national outcomes may be affected. It is a reliable source of information on population, tourism, and transit. If you're commuting to work, you may now study it. The position of a phone is determined by the cell's cellular base station. Out-of-range phones connect to the base stations. A mobile phone is required to make and receive phone calls. There is enough information to be gleaned from the first few calls. Using many cellphone base stations to make phone calls reveals a person's habits. A person's location may be inferred if they begin chatting from one base station and wind up talking from another. Call and/or SMS data may also be accessed for investigation purposes. Trends in mobile phone use might provide demographic information. For both social and economic reasons, LMT data was analyzed. Mobile phone data analytics is also possible. This enabled researchers to keep tabs on their subjects. On the 25th of May, 2018, the GDPR went into force. (Spadon, 2019)

Background:

GDPR applies to EU individuals' personal information. It was become illegal to transfer individual phone numbers and do other related conduct under the GDPR. Each mobile base station's total calls and unique users were submitted to researchers. Track down cell towers. Every 15 minutes, on average, calls and SMS were received. During this time period, there were a total of unique users. The area that a base station may provide coverage. They'd been tracked down. In a data loss of 19 records, more affluent areas saw a decrease in economic growth. Local economic hotspots were highlighted in 2017–2018 by changes in transportation and internal activities. employing mobile phone data to keep tabs on business activities and travel habits. a. A prior municipal research on seasonality and mobile phone use was used to compare these results with the new ones. In 2015, 2016, 2017, and 2018, they were categorized. Finally, we assessed the efficiency and dynamism of economic activity. Regional economic growth trends in Latvia were discovered by people travelling to and from their jobs. Data and actions may be better understood using this tool. Time is required for visualization and analytics. Mobile applications are widely used and have several advantages. Our approach is a combination of empirical and computational visual analytics.

Methodology

Every time you make or receive a telephone conversation or text or email, any mobile phone network operator will send customers a CDR (Contact Detail Record) file. It is feasible to ascertain a person's precise location at the beginning of a phone conversation since the locations of all base stations are publicly available. The maximum number of phone calls and texts, the number of random users, and the date/time intervals are all included in each database record. Location and antennas type of cell site is included. The regional growth index may be used for real-time or regular assessment, according to the authors. Using this method, regional governments may conduct a strategic gap analysis to monitor the execution of their plans.

 

By frequently assessing the strategic direction attained by local jurisdictions over time, regional administrations may use additional central outcome measures. As a consequence, a new index was established based on fake data from Latvian mobile telephone consumers. (Arhipova, 2018)

 

 

 

Findings 

From 2015 through 2018, 119 factors (a linear combination of total mobile telephone operations and unique visitors for all municipality) were constructed for each workday to categories townships based on the economic development. Using a Factorial rotation, the PCA was performed for the years 2015 to 2016, 2017 to 2018, as well as 2018 to 2019. Questionnaire appropriateness testing (KMO) was used to examine the applied PCA. With KMO values around 0.8 and 1, it is clear that the sample size is enough. On workdays, the first functional unit (PC) has high values, whereas the second PC has high values on Fridays and Saturdays for towns with little business growth. The KMO is 0.990, which explains 67.6 percent of the overall variance. There is a 71.0 percent variation in the wide variety of experiences in 2017 and a 77.7 percent variation in 2018 based on PCA results that are relevant. Figure 2 shows the average values of the critical parts for during the week and weeks (Figure 3 as shown). (Šćepanović, 2019)

Principal component analysis information revealed that there have been eight sets of townships in Latvia (including working days and weekend hours), which were as follows: 2015–2016, 2018, and 2019. As a first step, the effectiveness of the commercial activity plan was assessed using equation, with the effectiveness curves ranging from 40 percent to 100 percent of their maximum value. The efficiency curve is a valuable tool for evaluating the characteristics of various municipality and other organizations. (Wen, 2018)

Conclusions

This might monitor the region's economic success. The time between working days and vacations varies greatly. Based on Latvian municipal statistics, these eight categories We utilise each town's effectiveness curve. Aspects of season and economy Latvia's economy improved in 2017. Disinterested everywhere. In 2018, the number of communities with 95% to 100% productivity doubled. Saturdays and holidays are slower. We need more vacation. Prioritisation messes up resources Summer in Latvia is hot. Revise a town's strategic framework. Monitor in real-time or on request. Keep an eye on the strategy for strategic flaws. Within a city or county strategic direction may be seen. A Latvian phone data is used. Using anonymized smartphones for Compliance. Routing data from commuters. Human commuters signify freedom. Intensity changes day to day imply population shifts In 2017 and 2018, it was 7am-5pm. Weekends and holidays are busier. 5–7 p.m. We developed a technique to analyse internal population movements and seasonality.

 

References

 

1.      Spadon, Carvalho, A. C. P. L. F. de, Rodrigues-Jr, J. F., & Alves, L. G. A. (2019). Reconstructing commuters network using machine learning and urban indicators. Scientific Reports, 9(1), 11801–11813. https://doi.org/10.1038/s41598-019-48295-x

2.      Arhipova, Berzins, G., Brekis, E., Binde, J., Opmanis, M., Erglis, A., & Ansonska, E. (2018). Mobile phone data statistics as a dynamic proxy indicator in assessing regional economic activity and human commuting patterns. Expert Systems, 37(5), n/a–n/a. https://doi.org/10.1111/exsy.12530

3.      Šćepanović, Mishkovski, I., Hui, P., Nurminen, J. K., & Ylä-Jääski, A. (2019). Mobile phone call data as a regional socio-economic proxy indicator. PloS One, 10(4), e0124160–e0124160. https://doi.org/10.1371/journal.pone.0124160

4.      Wen, Hsu, C.-S., & Hu, M.-C. (2018). Evaluating neighborhood structures for modeling intercity diffusion of large-scale dengue epidemics. International Journal of Health Geographics, 17(1), 9–9. https://doi.org/10.1186/s12942-018-0131-2