Proceedings of The International Conference on Data Science and Official Statistics最新文献

{"title":"Estimation of Air Pollutants using Time Series Model at Coalfield Site of India","authors":"A. Choudhary, P. Kumar","doi":"10.34123/icdsos.v2021i1.59","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.59","url":null,"abstract":"Assessment of air pollutants and quality is an intricate task because of dynamic nature, unpredictability and high inconsistency in space and time. In this study, a time series moving average (MA) model is employed to estimate air pollutants (PM2.5, PM10, NO2, NOX, O3, SO2 and CO) over the coalfield site of India. The estimated O3 with Adj. R2 = 0.958 was identified as the most accurate estimation followed by other estimated pollutants. Though, results for the estimated PM2.5 (Adj. R2 = 0.950) and NO2 (Adj. R2 = 0.949) were found almost similar to the results of O3 (Adj. R2 = 0.958). The estimated CO with Adj. R2 = 0.887 was identified lower among all the estimated pollutants was also found very well. The existing results of the study demonstrate that MA model permits us to precisely estimate daily basis pollutant concentrations, for the different sites of India.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123487958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating Customer Lifetime Value in the E-Commerce Industry Using Multivariate Analysis","authors":"Bagaskoro Cahyo Laksono, I. Wulansari","doi":"10.34123/icdsos.v2021i1.161","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.161","url":null,"abstract":"Companies can develop their business using big data to support decision-making. Big data in the e-commerce industry that includes size and speed of high transactions can be used to analyze customer behaviour and predict customer value. Nowadays, companies are starting to develop customer-oriented rather than product-oriented business interests. One way that can be used to determine customer value is by calculating Customer Lifetime Value (CLV). By knowing CLV at the individual level, it will be useful to help decision-makers to develop customer segmentation and resource allocation. It is important to do segmentation or customer grouping that describes customer loyalty groups. Therefore, this research aims to calculate CLV and customer segmentation using the RFM analysis method. The dimensions of forming CLV include the values of Recency, Frequency, and Monetary. In this study, concept of multivariate statistical analysis will be applied, namely K-Means Clustering and factor analysis. Segmentation is done to determine the level of customers. The higher the CLV value, more valuable customer is to maintain. In the end, the customer segmentation method built by author can be used to optimize company's strategy to get maximum profit. This method can be applied to various cases and other companies.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126220756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bayesian Network Model to Distinguish COVID-19 for Illness with Similar Symptoms","authors":"Emir Luthfi, A. Wijayanto","doi":"10.34123/icdsos.v2021i1.36","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.36","url":null,"abstract":"Numerous diseases and illnesses exhibit similar physical and medical symptoms, such as COVID-19 and its similar disguised illness (common cold, flu, and seasonal allergies). In this study, we construct a Bayesian Network model to distinguish such symptom variables in a classification task. The Bayesian Network model has been widely used as a classifier comparable to machine learning models. We develop the model with a scoring-based method and implement it using a hill-climbing algorithm with the Bayesian information criterion (BIC) score approach. Experimental evaluations using publicly available Mayo Clinic based data using this Bayesian Network model that present Directed Acyclic Graph (DAG) which can show the relationship between the similar symptoms and the type of disease with Conditional Probability Table (CPT). This model shows a promising accuracy performance up to 93.14% which is better than the performance of other machine learning classifiers, including the Support Vector Machine (SVM) and the ensemble approaches such as Random Forest (RF), while slightly smaller than that of the neural networks (NN).","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126273303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Government Policy in Handling Covid-19 in Indonesia","authors":"Atika Kautsar Ilafi, Annisa Nur Fadhilah, Lita Jowanti","doi":"10.34123/icdsos.v2021i1.152","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.152","url":null,"abstract":"The Covid-19 pandemic has affected the economy in many countries, including Indonesia. Until July 2021, the Government has implemented social activity policies for the community, starting from Large-Scale Social Restrictions in the first semester of last year to PPKM Level 4 to stop the spread of Covid-19. Responding to the Covid-19 pandemic, Google released data from people who access google applications using mobile devices. The Google Mobility report shows changes in population activity and mobility in several locations. This study aims to examine the effect of the PSBB and PPKM policies in Indonesia on the decline in COVID-19 cases in Indonesia using the Google Mobility Index and their impact on the economy in Indonesia. The analysis uses graphs and Pearson Correlation and Long Short-Term Memory (LSTM) method to predict Covid-19 cases and mobility data. The result shows that the mobility of people to five places has a significant effect on the number of daily cases of Covid-19, while there is a significant effect on three places of community mobility on Indonesian economic. As the results, controlling the spread of Covid-19 is better prioritized than economic condition.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127380750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data Collection Improvement: Daily Self-Enumeration Accommodation Survey","authors":"Ignatius Aditya Setyadi","doi":"10.34123/icdsos.v2021i1.168","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.168","url":null,"abstract":"Until now, BPS - Statistics Indonesia has conducted monthly accommodation surveys both for the star and non-star accommodation categories to provide information on commercial accommodation activities at the national and regional levels. Both star and non-star accommodation categories are done by complete enumeration in each region. Statistics include guest night and room capacity to obtain the occupancy rate of a hotel room. The data contains daily accommodation information that is collected every month, so then it will be entered completely in each region following the observation month. Due to the timeliness requirements for monthly press releases, BPS has implemented online data entry since 2017. It may seem obvious, regions that have more interest will have an impact on a bigger number of accommodations, which also affects the number of enumerators and may lead to such problems especially in response burden. Unfortunately, the same problem is also not easily avoided by regions with less accommodation, mostly due to the distance issues to the accommodation area and its spread in the region. Therefore, a new data collection strategy is required to provide respondents with convenience in order to increase response rates, as well as to reduce the workload of enumerators which also leads to the lower cost. The outbreak of COVID-19 has posed unprecedented problems for National Statistical Offices (NSOs) around the world, including BPS – Statistics Indonesia. This crisis has led us to think in new ways and make decisions that will change our statistical operations in order to meet ongoing data needs even throughout the epidemic. The purpose of this paper is to discuss the evolution of accommodation surveys, which are designed to not only solve problems but also achieve objectives. Currently, there are nearly 180 active users of this self-enumeration accommodation survey for about 142 distinct accommodations across Indonesia. Moreover, this addition has proven to have succeeded in increasing the response rate average from 57.17% in 2020 to 68,35% in 2021.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129163835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of Shifting Large and Medium-Sized Industry Agglomeration on the Economic Development in Kanti Region in 2003-2018","authors":"A. Maulana, Ekaria Ekaria","doi":"10.34123/icdsos.v2021i1.83","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.83","url":null,"abstract":"The development of real Gross Domestic Regional Product (GDRP) 2010 of all cities in Kanti region increased during 2003-2018. However, when viewed the growth rate in aggregate, it slowed during the period 2010-2018. One of the causes is the shift of large and medium-size industry (LMI) agglomeration from Kanti region to Kangga region. This study aims to find out the location and the dynamics of the shift of LMI agglomeration using the Hoover-Balassa index that is presented through thematic maps. In addition, the study also analyses the effect of the shift of LMI agglomeration and other factors on economic growth in Kanti region using the regression analysis of panel data. The individual units used are five administrative cities in the Kanti region with annual units from 2003 to 2018. Fixed effect model with seemingly unrelated regression (FEM-SUR) is used to estimate the parameters of the economic growth model in Kanti region. The results showed that Kanti region was agglomerated in North Jakarta and East Jakarta. Labor-intensive potential factor has a negative and significant effect, while the labor productivity of LMI and domestic investment has a positive and significant effect on economic growth in Kanti region. North Jakarta is an area that despite the shift of LMI agglomeration but still able to increase its economic growth, while East Jakarta has decreased. So, the Provincial Government of Jakarta need to adapt the implementation of LMI agglomeration in North Jakarta to encourage economic growth in East Jakarta and West Jakarta in accordance with regional spatial planning for industry.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128859520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Micro and Macro Determinants of Precarious Employment in Indonesia: An Empirical Study of Paid Workers using Multilevel Binary Logistic Regression","authors":"Mohammad Rifky Pontoh, Nucke Widowati Kusumo Projo","doi":"10.34123/icdsos.v2021i1.68","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.68","url":null,"abstract":"Decent work for all is one of the goals stated in the Sustainable Development Goals (SDGs). One indicator that can represent proper work conditions is the precarious employment rate (PER). In recent periods, the precarious employment rate in Indonesia has shown an increasing trend. It indicates a decent work deficit in Indonesia. In addition, the PER among provinces has a different figure. This study aims to analyze the micro and macro factors that influence the status of precarious employees in Indonesia. The analytical method used in this study is multilevel binary logistic regression. The results show that micro factors; namely the worker's characteristics, including age, education level, employment sector, previous work status, and urban-rural area; have a significant effect on the precarious status of employees. In terms of macro factors, it is found that an increase in the output of the industrial and construction sectors can reduce the tendency of a worker to become a precarious employee. Meanwhile, an increase in labour supply increases the likelihood of workers becoming precarious employees. Various parties, including society and government, have to put extra efforts to reduce the precarious employment rate by improving the quality of human capital and domestic products demand.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133093083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Impact of Domestic Investment, Foreign Investments, HDI, Export, and Import on the Economic Growth in Indonesia","authors":"Lutfia Septiningrum, Paramita Dewanti, Fauzah Hikmawati","doi":"10.34123/icdsos.v2021i1.165","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.165","url":null,"abstract":"The aims of this study were to examine the causal relationship between domestic investment, foreign, Export, Import, HDI and their impact on Indonesia's economic growth measure with GDP. The data used was panel data from 18 provinces in 2016-2020 which was taken based on stratified random sampling. The model used to complete the purpose of this research was panel data regression. The results of the analysis show economic growth based on the value of GDP in each province tends to decline. Modelling of economic growth in Indonesia was used Panel Data Regression. In this research, Hausman Test is used to obtain the best model of panel data regression because the model contain of Random Effect Model. Based on Simultaneous test results obtained at least one significant variable to the model and based on partial test the GDP was significantly influenced by the variables of FDI, DDI, HDI and Import sectoral value. Variable Export has an effect on GDP but is not significant where R2 shows the results of 98.9%","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121315955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AMDA: Anchor Mobility Data Analytic for Determining Home-Work Location from Mobile Positioning Data","authors":"Amanda Pratama Putra, Wa Ode Zuhayeni Madjida, Ignatius Aditya Setyadi, Amin R. S. Nugroho, A. R. M. Munaf","doi":"10.34123/icdsos.v2021i1.239","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.239","url":null,"abstract":"In conducting a mobility analysis using Mobile Positioning Data, the most critical step is to define each customer's usual environment. The initial concept of mobility used is the movement that occurs from and to every usual environment, so errors in determining the usual environment will cause incorrect mobility statistics. Therefore, Anchor Mobility Data Analytic (AMDA) is proposed for Home-Work Location Determination from Mobile Positioning Data. This algorithm uses clockwise reversal to make it easier to classify someone in their usual environment. Unfortunately, only about 80% of the raw data can be used to establish usual environments. The remaining 20% do not have sufficient data history. This study found that the accuracy of AMDA in determining monthly home location was 98.8% at the provincial level and 88.7% at the regency level. As for the determination of monthly work locations, 98.9% at the provincial level and 70.4% at the regency level.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114988130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of Student's Dropout Early Warning System Using Analytical Hierarchy Process","authors":"Naflah Ariqah, Yunarso Anang","doi":"10.34123/icdsos.v2021i1.201","DOIUrl":"https://doi.org/10.34123/icdsos.v2021i1.201","url":null,"abstract":"As a higher education institution, Politeknik Statistika STIS also faces the same problems as universities in general, those are student failing to compare that year courses thus have to repeat those courses or student dropping out. To overcome this problem, this research proposes a Dropout Early Warning System (DEWS) that can provide early warnings for dropouts and repeat a class. With this system, it is hoped that it can help institutions to identify students who have the potential to drop out or repeat a class. The purpose of making this system is to help academic supervisors and decision makers from Polstat STIS in knowing the potential for student. The potential for students to drop out and repeat a class is measured by a potential score obtained from the results of an assessment of 5 criteria consisting of GPA scores, gender, economic factors, violation points, and record of repeating class. Prediction results are presented in three categories consisting of low potential, medium potential, and high potential which are calculated from the results of weighting calculations using the Analytical Hierarchy Process (AHP). The system is tested and verified using Black Box test and the evaluation of the calculation method using confusion matrix. Based on the test results, the functions that exist in the system can function properly and can supply the needs.","PeriodicalId":151043,"journal":{"name":"Proceedings of The International Conference on Data Science and Official Statistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130882866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}