Towards Quality Data in the Big Data Age

One key to being able to win the competition between countries is to have strategic, accurate and quality data. Data that is able to answer the challenges of the times. There is a strong correlation between a country's ability to grow and the availability of quality data. In this case, the role and commitment of the Central Statistics Agency (BPS) is very much needed to support the availability of data needed by the government, the business world and the community. The institution that carries the vision of "Providing Quality Statistical Data for Advanced Indonesia" has a very strategic role. In the past, each ministry or agency could publish its own version of sectoral data, now the Central Statistics Agency has been mandated as the “sole supplier” of data for the government. As an official government agency in charge of dealing with statistics in accordance with applicable laws and regulations, the Central Statistics Agency must be able to provide quality data in the sense of complete, accurate, timely, correct, and relevant. Quality data, for the Central Bureau of Statistics is a necessity. Because the mission of the Central Bureau of Statistics is to provide quality statistical data of national and international standards, to foster K/L/D/I through a sustainable National Statistical System. Realizing excellent service in the field of statistics for the realization of the National Statistical System and Building superior, adaptive Human Resources based on the values ​​of professionalism, integrity and trust. Quality data will fulfill all dimensions of statistical quality called the Quality Assurance Framework (QAF). which includes relevance, accuracy, actuality, timeliness, accessibility, coherence, comparability and interpretability. In each implementation, it always refers to the concept of standards and methods that apply universally and with international standards. So that the resulting data and indicators have comparability at the national and international levels. Actually, the data quality of the Central Bureau of Statistics is getting better from time to time. This is evidenced by the increasing number of domestic institutions, both government agencies, the business world and the general public as well as international institutions that use the publication of data from the Central Statistics Agency. The trust of data users in the data produced by BPS must be continuously improved. Indeed, the resulting data is not presented to please all parties, but must refer to the actual conditions. Such data can be used as guidelines for steps and signs for making improvements so that development goals can be achieved.

Improved data quality does not happen immediately. Besides the need for reliable human resources, the performance of the Central Statistics Agency today must also involve technology. The process of searching and processing data needs to be supported by innovation in line with the latest technological developments. The emergence of new sources of data and information requires new handling, both in terms of data collection and processing. On the other hand, data users demand the availability of fast and accurate data. Government programs, such as the response to Covid-19, for example, require fast data support. Today's business actors are also competing to collect data from various sources to be able to exist in their business competition. The better the data management and the faster the availability of data, the more sustainable products can be created so that they provide good value for consumers. For this, inevitably the pattern for data collection and data processing will experience a shift. The methodology that has been used so far needs to be adapted to the changing conditions. Renewal of research techniques must shift from conventional to digital-based research. This change is due to the development of digital society and changes in the concept of digital sociology that are sweeping the world today. Moreover, the current pandemic condition has also accelerated the acceleration of this digital transformation. In this case, the Central Bureau of Statistics has implemented digital-based methods in data collection. If before the pandemic, census and survey activities could be carried out by direct interaction with the community, now adaptations and changes have been made in conducting censuses and surveys due to the limitations of face-to-face meetings. To facilitate research activities in the midst of the Covid-19 pandemic, which requires redesign of the census and surveys for data collection, BPS has also combined the digital/online method with the direct interview method. Utilization and technical mastery of digital methods will continue to be carried out by the Central Statistics Agency, one of which is the use of big data. Big Data is a general term that refers to technologies and techniques for processing and analyzing large amounts of data, both structured, semi-structured and unstructured.

Sources of big data are very abundant, including mobile phone data, financial transactions, online searches, satellite imagery, sensors in cities, transportation and homes, sensors in nature, agriculture and water, biometric data, Internet of Things (IoT). , social media data, health records and radio content. To be able to provide useful value, data must go through various stages of processing first. Starting from recording / creation, collection, storage, enrichment, analysis and further processing, to presentation. The most important aspect of big data is actually not just how much data can be stored and processed, but what use or added value can be obtained from the data. If we can't extract the added value, then the data will just be useless garbage. This added value can be used for various things, such as improving operational fluency, accuracy of sales, improving service quality, market predictions or projections, and so on. The implementation of big data at the Central Bureau of Statistics has been carried out since 2015 using various existing big data sources. The use of Mobile Positioning Data (MPD) continues to be developed to support the estimation of the number of foreign tourists, for event analysis such as the 2018 Asian Games, monitoring the mobility of commuters, the movement of Nusantara Tourists, National Tourists (Tourism Statistics), and supporting the preparation of the Metropolitan Statistical Area delineation. Satellite images are used in the Area Sampling Framework activity to obtain accurate agricultural data. Other big data sources and Artificial Intelligence initiatives are also implemented as part of the acceleration of statistical business processes at the Central Bureau of Statistics. Today in the future the Central Statistics Agency is expected to increase cooperation with all parties, both ministries/agencies, local governments, research institutions, businesses and universities to conduct joint research and publications. The quality of BPS data, which is already credible and representative, needs to be followed up continuously by making innovations in terms of presenting interesting data and information, easier access, and guaranteed data quality. Today in the future, the Central Statistics Agency will continue to face the challenges of the times because its data will always be compared with big data. And I'm sure BPS will be able to handle it.