2021 and BEYOND by Andry Alamsyah
Economies, 2022
Halal meat is an essential product outputted by the halal food industry. It is a part of the broa... more Halal meat is an essential product outputted by the halal food industry. It is a part of the broader concept of the halal economy, an economic activity that follows the Islamic-based principle. As the world's most populous Muslim country, Indonesia has not fully tapped the market's potential. Presently, providing halal assurance to society is a task for halal bodies supported by the Indone-sian government; three halal bodies work together to guarantee the halal supply chain. However, the current process does not provide enough transparency, traceability, and granularity of infor-mation. Blockchain may potentially answer the challenge and offer an innovative approach as new emerging technology. This study’s first objective is to discuss how to improve the current practice of halal assurance in the meat industry as a part of the Indonesian halal supply chain ecosystem. The second objective is to construct a traceability model to support the halal supply chain using blockchain technology. We conducted the research by interviewing the stakeholder to collect business process information and followed by constructing the model for blochainable business process. The completed model will provide an innovative base for the national standard and further implementation in Indonesia's new halal ecosystem.
IEEE Access, 2022
The COVID-19 pandemic has adversely affected households' lives in terms of social and economic fa... more The COVID-19 pandemic has adversely affected households' lives in terms of social and economic factors across the world. The Malaysian government has devised a number of stimulus packages to combat the pandemic's effects. Stimulus packages would be insufficient to alleviate household financial burdens if they did not target those most affected by lockdowns. As a result, assessing household financial vigilance in the case of crisis like the COVID-19 pandemic is crucial. This study aimed to develop machine learning models for predicting and profiling financially vigilant households. The Special Survey on the Economic Effects of Covid-19 and Individual Round 1 provided secondary data for this study. As a research methodology, a cross-industry standard process for data mining is followed. Five machine learning algorithms were used to build predictive models. Among all, Gradient Boosted Tree was identified as the best predictive model based on F-score measure. The findings showed machine learning approach can provide a robust model to predict households' financial vigilances, and this information might be used to build appropriate and effective economic stimulus packages in the future. Researchers, academics and policymakers in the field of household finance can use these recommendations to help them leverage machine learning.
Economies, 2022
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
International Conference on Data Science and Its Applications (ICoDSA), 2021
Information from news and social media is an integral part of business and investment activity. F... more Information from news and social media is an integral part of business and investment activity. Following the advancement of social media, the public's opinion has become abundant. Instagram, Facebook, and Twitter are social media platforms that have recently received much attention from the crowd. Furthermore, the sentiment of headline news can also show that stock price depends on the company's profit or loss. In the view of the electric car's issue, this study observes the public's opinion for car brands to examine the correlation between the stock price and the sentiment from social media and headline news by Pearson correlation. The results show a reasonably strong correlation between the public sentiment in social media and headline news with the rise and fall in stock price. The benefit of this research is for investors about public sentiment towards brands produced by these companies who want to invest in the capital market to make the right decisions.
2nd International Conference on ICT for Rural Development (IC-ICTRuDev), 2021
Indonesia is ranked 56th in the Digital Competitiveness Ranking; the survey considers various fac... more Indonesia is ranked 56th in the Digital Competitiveness Ranking; the survey considers various factors: knowledge, technology, and future-readiness of digital expertise. One entity expected to meet the needs of digital expertise to serve future readiness in digital competitiveness is the government. One way to explore digital expertise in Indonesia is by identifying top talents from data owned by a regional public service. We identify top talents with sufficient digital competence using interviews and questionnaires as media for collecting data between employees using Social Network Analysis (SNA) methodology. This study identifies and maps the best digital talents based on their digital competencies measured by network centrality. The result shows the SNA model represents a digital talent mapping network as a recommendation for the government to improve their digital talents competency, thus developing overall organization performance. The contributions of this study are first to show the best 10 actors as digital expertise at the organization with the accumulation of digital competencies values in these actors. Second, it provides new insight into the talent mapping method, especially in human resources, to increase the potential of digital talent in a regional public service from the results of the centrality measurement.
2nd International Conference on ICT for Rural Development (IC-ICTRuDev), 2021
Human resources (HR) recruitment strategy is vital for companies to compete; recruiting suitable ... more Human resources (HR) recruitment strategy is vital for companies to compete; recruiting suitable job applicants is an exhaustive and complex process. HR can identify job applicants effectively and efficiently with the help of information and communication technology. There is fierce competition between companies following the advancement of the digital industry. Currently, it is possible to identify prospective job applicants using a personality measurement based on an ontology model using social media data. The development of the ontology model with the addition of 2399 corpus ontologies resulted in accurate and diverse personality analysis. Therefore this ontology model is proposed to analyze personality effectively and affordable based on sizeable textual data. The subjects of this study are 5 Twitter users whose data is available on social media. We collect their tweets to characterize their expression or opinion. Textual data from those users totaling 3744 data is processed with an ontology model for measuring personality based on the Big Five Personality Traits. This research shows that job applicants have different dominant personalities such as Extraversion, Agreeableness, Conscientiousness, and Openness. The personality possessed by these job applicants is accurate based on the validation and verification by the psychologists or domain experts. This approach is helpful for the HR department in terms of knowing job applicants' personalities and deepening their understanding of personality.
International Conference Advancement in Data Science, E-learning and Information Systems (ICADEIS), 2021
The popularity of various tourist destinations in Indonesia makes the tourism industry an essenti... more The popularity of various tourist destinations in Indonesia makes the tourism industry an essential pillar of the Indonesian economy sector. Understanding tourist behavior while visiting Indonesia plays a vital role in determining a suitable tourism strategy by knowing the tourist movement. But monitoring tourist movement is a nontrivial problem. Therefore, this study uses data sources based on tourist reviews on social media. The data is then applied to form the network based on network science that models their movements in Indonesia. The authors pick Lombok and Bali to represent this study because both islands are the most popular tourist destinations. This study models a complex representation of tourist movement, finds tourist movement directions to recognize their favorite destinations, and find the group of location preferred by tourist through network visualization. The study will be beneficial for policymakers, business opportunities, and the tourism office.
Journal of Science and Technology Policy Management, 2021
Purpose
The development of information technology is highly influential to all sectors, including... more Purpose
The development of information technology is highly influential to all sectors, including the financial industry. Various transformations are made in overcoming the dynamics of technological advancements, including the mapping of human resources. This study is conducted in the banking industry and companies operating using financial technology (FinTech) in Indonesia. This study aims to identify talent competencies needed in the future, based on current conditions and future needs, through mapping talent in the banking and FinTech industries.
Design/methodology/approach
This study provides empirical evidence about the mapping of talent management with eight basic competencies. It uses a mixed-method, explanatory sequential with survey approach in the first phase and focus group discussions (FGD) in the second phase. The questionnaire is distributed to 309 respondents who are the specific decision-makers in this industry. Meanwhile, the FGD is conducted twice at different times with academics and practitioners, human resources and talent managers. This research used analytic hierarchy process as a tool for data processing.
Findings
This study provides current competency positions and future needs in the banking and FinTech industries in Indonesia where it found a lot of competence segregation. It also discovered three priority competencies for dealing with Industry 4.0, which included relating and networking, adapting and responding to change and entrepreneurship and commercial thinking.
Practical implications
This study is valuable for decision-makers and regulators; these results can be used to find new competencies and talents to develop existing human resources. Also, these results can be used as a basis for policy-making related to the Industrial Revolution 4.0.
Originality/value
This study provides new insights on talent mapping in the banking and FinTech industries as a strategic approach in the digitalization era. In addition, this research also adds knowledge related to Industry 4.0 as a result of industry developments in the digitalization era.
Information, 2021
Human online activities leave digital traces that provide a perfect opportunity to understand the... more Human online activities leave digital traces that provide a perfect opportunity to understand their behavior better. Social media is an excellent place to spark conversations or state opinions. Thus, it generates large-scale textual data. In this paper, we harness those data to support the effort of personality measurement. Our first contribution is to develop the Big Five personality trait-based model to detect human personalities from their textual data in the Indonesian language. The model uses an ontology approach instead of the more famous machine learning model. The former better captures the meaning and intention of phrases and words in the domain of human personality. The legacy and more thorough ways to assess nature are by doing interviews or by giving questionnaires. Still, there are many real-life applications where we need to possess an alternative method, which is cheaper and faster than the legacy methodology to select individuals based on their personality. The second contribution is to support the model implementation by building a personality measurement platform. We use two distinct features for the model: an n-gram sorting algorithm to parse the textual data and a crowdsourcing mechanism that facilitates public involvement contributing to the ontology corpus addition and filtering.
The 9th ICOICT, 2021
Given the rapid evolution of information technology increases the number of individual tourists w... more Given the rapid evolution of information technology increases the number of individual tourists who choose to enjoy free travel without depending on guidebooks and tour agency services. Information sharing activities continue without limitation facilitate most tourists to explore and independently decide their destinations based on online traveler review pages. This freedom generates an increasingly complex tourist visiting pattern. On other side, the abundance of data provides a new approach in analyzing this visiting pattern. We processed 214,228 reviews written by tourists all over the world regarding tourist destinations in Bali, Indonesia. This research analyzes the online traveler review data through association rule mining techniques to detect pairs of tourist’s destinations and mapped them through the network analysis approach. We separate our exploration by tracing the tourist visiting movement as the underlying factor to understand tourist visiting behavior. We discovered the most popular tourist destination pair in one trip is Tegalalang Rice Terrace and Sacred Monkey Forest Sanctuary, and there are differences in tourist visit preferences for each tourist origin continent but still have identical main choices. This research contributes to supporting efficient mobility in tourism management by providing tourism destination networks insight.
9th ICOICT, 2021
The development of Indonesia's ICT environment has made the mobile video-on-demand (VOD) platform... more The development of Indonesia's ICT environment has made the mobile video-on-demand (VOD) platform one of the emerging lifestyles. With advanced smartphone technology, mobile phone subscribers able to enjoy high-resolution mobile VOD service with a greater user experience. The purpose of this study is to profile and predict potential customers of one of the VOD platforms, Netflix, for personalizing marketing targets. Using machine learning predictive analytic methodology, customer profile and behavior data are divided into 3 clusters using the K-Means model before tested with several supervised models for getting the best model for each cluster. Feature importance analysis is conducted to support marketing insight for product offering follows up to each targeted potential customer. Significant variables affecting Netflix buyers and non-buyers within 3 different clusters are defined clearly with the number of potential customers that can be targeted as Netflix's future subscribers. The result shows the method can be used by the mobile operator to target potential customers with effective promotional or product offering by personalized marketing approach based on the behavioral pattern and customer needs. It is expected by implementing this methodology, effectivity and accuracy of marketing effort will be increased compared to the conventional method.
9th ICOICT, 2021
The high number of social media actors has the potential to produce fake news. Fake news could be... more The high number of social media actors has the potential to produce fake news. Fake news could be motivated by various agendas, such as politics, government, and health. Therefore, we need to know how the mechanism and measurement of the spread of fake news. One approach to studying the spread of it is the information cascade. This paper will model the information cascade mechanism using Social Network Analysis (SNA) and Susceptible-Infected (SI) model. SNA is adopted to investigate the spreading mechanism and determine the proportion of actors exposed to fake news. SI is applied to measure the speed of transmission of fake and true news. Using several topic samples, the results allow us to understand the mapping of cascade information from fake news by a level that differentiates the node level from the source news to the rest of the nodes in the network. Our finding fake news can reach 0,6414 more fractions and spread 4,6 times faster than true news.
IOP Conf. Ser.: Mater. Sci. Eng. 1098 052103, 2021
Financial investment has become a trend in Indonesia with significant increase of active investor... more Financial investment has become a trend in Indonesia with significant increase of active investors since 2015. Before making an investment, the investors need a comprehensive analysis to reduce the chances of failure that result in financial distress, the same apply towards companies in order to organize its financial strategies. Financial distress indicated by losing its value, ineffective production, cash flow problems or high financial leverage value. These conditions threaten the companies and the investors who face significant financial loss. The purpose of this research is to construct early warning model of financial distress, by examining the phenomenon of 90 companies in Indonesia, from 2015 to 2018 listed on Indonesia Stock Exchange (IDX). We apply Artificial Neural Network (ANN) backpropagation methodology using financial indicators such as profitability, liquidity, and solvability as the inputs. We divide the ANN model into time categories that is t-2, t-3, and t-4. In constructing ANN model, we configure four types of splitting training and testing data. The results show that ANN backpropagation model with 30 neurons, 90% training data and 10% testing data in category t-4 works well an accuracy 95.6% for financial distress prediction in Indonesia.
2020 by Andry Alamsyah
2020 International Conference on Data Science and Its Applications (ICoDSA), 2020
The ability to predict the stock price is the important factor in achieving the profit in stock i... more The ability to predict the stock price is the important factor in achieving the profit in stock investment, and the prediction is usually done by relating the price of a stock to factors that influence it. The problem is, there are a large number of variables that can be used to predict the stock prices so it is difficult for a potential investor to choose which variables should be used in predicting the stock prices. This research used the Principal Component Analysis as the dimension reduction method to form major components that influence the stock prices without losing the information and uses data from five companies which have the highest market capitalization that listed in the Consumer Goods Sector of the Indonesia Stock Exchange: Companies A, B, C, D, and E. Using Principal Component Analysis, this research reduces eighteen variables into factors that influence the stock price the most. Result shows that Profitability Ratio has a high contribution in determining stock price.
2020 8th International Conference on Information and Communication Technology (ICoICT), 2020
The burgeoning need of a brand ambassador (BA) as a company representative begin to rise in recen... more The burgeoning need of a brand ambassador (BA) as a company representative begin to rise in recent year. The phenomena followed by the increase of method to select the most suitable BA. The universal way of selecting one appropriate ambassador is by understanding their personality, therefore, measurement of a BA personality considered as one way to characterize a company credibility. This research proposes to design a method of measuring the BA personality from their social media data in Bahasa Indonesia. We enrich the methodology to measure human personality using the ontology modeling approach. The ontology model constructed under the ngram language model which provides a rapid and effective way of measuring a BA personality. The results of a BA personality measurement allow the utilization to portray of how an ambassador represent their brand and interact with their customer.
2020 8th International Conference on Information and Communication Technology (ICoICT), 2020
In recent years, Online Travel Agencies (OTA) is widely used by people due to its simplicity and ... more In recent years, Online Travel Agencies (OTA) is widely used by people due to its simplicity and efficiency. Tight competition between industries makes companies must pay attention to the quality of their services since it is capable to enhance customer satisfaction. To evaluate its service, the company needs to comprehend their position as OTA providers. Users' opinion in social media is essential for recognizing the company performances. In this case, sentiment analysis and multiclass classification methods help the company to understand their service quality specifically. As a case study, we use the most popular Online Travel Agencies (OTA) providers in Indonesia: Traveloka, Tiket.com, and Pegipegi. Based on our criterion, we examine fulfillment and responsiveness dimensions of these three OTA providers. We apply Naïve Bayes Classifier (NB) model to classify users' opinions. This model has accuracy around 75-85% for the three OTA providers. The result reveals that Pegipegi obtains better service quality with 57% positive and 43% negative sentiment than Traveloka and Tiket.com with 56% positive and 44% negative. The overall result shows general topics of fulfillment and responsiveness dimensions are related to the ticket availability and customer service performances.
Test Engineering and Management, 2020
Top line hotels are now shifting into the digital way in how they understand their customers to m... more Top line hotels are now shifting into the digital way in how they understand their customers to maintain and ensuring satisfaction. Rather than the conventional way which uses written review or interviews, the hotel is now heavily investing in Artificial Intelligence particularly Machine Learning solutions. Analysis of online customer reviews changes the way companies make decisions in a more effective way than using conventional analysis. The purpose of this research is to measure hotel service quality. The proposed approach emphasizes on service quality dimensions reviews of the top-5 luxury hotel in Indonesia that appear on online travel site TripAdvisor based on section "Best of 2018". In this research, we use a model based on a simple Bayesian classifier to classify each of customer review into one of service quality dimensions. Our model was able to separate each classification properly by accuracy, kappa, recall, precision, and F-measure measurements. To uncover latent topics in the customer opinion we use Topic Modelling. We found that the common issues occur is about responsiveness as it got the lowest percentage compared to others. Our research provides a faster outlook of hotel rank based on service quality to end customer based on a summary of the previous online review.
Advance in Science, Technology and Engineering Systems Journal, 2020
Human behavior quantification is an essential part of psychological science. One of the cases is ... more Human behavior quantification is an essential part of psychological science. One of the cases is measuring human personality. Social media provide rich text, which can be beneficial as a data source to get valuable insight. Previous researches show that social media offered favorable circumstances for psychological researchers by tracking, analyzing, and predicting human character. In this research, we propose a personality measurement design to help to assess human character through linguistic usage from human digital traces. We construct our model by classifying social media text to the pre-determined personality facet from Big Five personality traits, mapping the knowledge to the ontology model, and implementing the model as a platform dictionary. Our model is based on the Indonesian language, which to the best of our knowledge is the first in the subject area. The platform is running effectively by using a well-established sorting algorithm, called the radix tree. Our objective is to support psychological science in adapting to a new technological era.
Journal of Theoretical and Applied Information Technology, 2020
The instability of financial system issues might trigger a bank failure, evoke spillovers, and ge... more The instability of financial system issues might trigger a bank failure, evoke spillovers, and generate contagion effects which negatively impacted the financial system, ultimately on the economy. This phenomenon is the result of the highly interconnected banking transaction. The banking transactions network is considered as a financial architecture backbone. The strong interconnectedness between banks escalates contagion disruption spreading over the banking network and trigger the entire system collapse. This far, the financial instability is generally detected using macro approach mainly the uncontrolled transaction deficits amount and unpaid foreign debt. This research proposes financial instability detection in another point of view, through the macro view where the banking network structure are explored globally and micro view where focuses on the detailed network patterns called motif. Network triadic motif patterns used as a denomination to detect financial instability. The most related network triadic motif changes related to the instability period are determined as detector. We explore the banking network behavior under financial instability phenomenon along with the major religious event in Indonesia, Eid al-Fitr. We discover one motif pattern as the financial instability underlying detector. This research help to support the financial system stability supervision.
International Journal of Innovation, Creativity, and Change, Mar 1, 2020
We have seen that some of social opinion polarization leads to the breakup of the relationship, s... more We have seen that some of social opinion polarization leads to the breakup of the relationship, some in the scale of small communities, but others can divide large organizations or even a nation. The legacy methodology to answer the root cause of opinion polarization in the society commonly use random sampling and questionnaire approach. This approach generally expensive in term of time and money. On the contrary, we have the opportunity to employ big data approach using social media data. Big data methodology provides us the rich source to investigate several questions, such as: how social opinion polarization formed, dynamic social network mechanism during time-windows observation, identification of dominant actors and communities. The power of big data approach lies in the number of data analyzed, where the more data involved in the process, the more accurate to describe the population condition. Today, computing power is no longer become an obstacle to process large volume, fast, and variety data, thus the observation of social opinion polarization process is possible. In this research, we answer the social opinion polarization root cause by using topic modelling methodology. The dynamic social network mechanism is measured using social network properties. Identification of influential actors and communities are provided by social network analysis metric and methodology. By answering three major questions above, we are able to explain of opinion polarization and its growth along the time, both for their topology structure and conversational content. The process knowledge gives us insight to how and when the separation takes place. As a case study, we use two massive adverse political campaign in Indonesia regarding the opinion of pro and contra the incumbent president to continue his presidentship in 2019 presidential election. We benefited of Indonesian habit to produce user-generated content in term of post and conversation in social media. We collect Twitter data with the following information: the observation duration is 10 days from April 27 th to May 2 nd , 2018, data collected based on several opposite hashtags such as #2019GantiPresiden #Jokowi2Periode and many more, we acquire 24097 and 418256 tweets from pro and contra movement. The benefit of this study is to avoid the danger of deepening gap between opponent communities by implementing right strategy to prevent that from happen.
Uploads
2021 and BEYOND by Andry Alamsyah
The development of information technology is highly influential to all sectors, including the financial industry. Various transformations are made in overcoming the dynamics of technological advancements, including the mapping of human resources. This study is conducted in the banking industry and companies operating using financial technology (FinTech) in Indonesia. This study aims to identify talent competencies needed in the future, based on current conditions and future needs, through mapping talent in the banking and FinTech industries.
Design/methodology/approach
This study provides empirical evidence about the mapping of talent management with eight basic competencies. It uses a mixed-method, explanatory sequential with survey approach in the first phase and focus group discussions (FGD) in the second phase. The questionnaire is distributed to 309 respondents who are the specific decision-makers in this industry. Meanwhile, the FGD is conducted twice at different times with academics and practitioners, human resources and talent managers. This research used analytic hierarchy process as a tool for data processing.
Findings
This study provides current competency positions and future needs in the banking and FinTech industries in Indonesia where it found a lot of competence segregation. It also discovered three priority competencies for dealing with Industry 4.0, which included relating and networking, adapting and responding to change and entrepreneurship and commercial thinking.
Practical implications
This study is valuable for decision-makers and regulators; these results can be used to find new competencies and talents to develop existing human resources. Also, these results can be used as a basis for policy-making related to the Industrial Revolution 4.0.
Originality/value
This study provides new insights on talent mapping in the banking and FinTech industries as a strategic approach in the digitalization era. In addition, this research also adds knowledge related to Industry 4.0 as a result of industry developments in the digitalization era.
2020 by Andry Alamsyah
The development of information technology is highly influential to all sectors, including the financial industry. Various transformations are made in overcoming the dynamics of technological advancements, including the mapping of human resources. This study is conducted in the banking industry and companies operating using financial technology (FinTech) in Indonesia. This study aims to identify talent competencies needed in the future, based on current conditions and future needs, through mapping talent in the banking and FinTech industries.
Design/methodology/approach
This study provides empirical evidence about the mapping of talent management with eight basic competencies. It uses a mixed-method, explanatory sequential with survey approach in the first phase and focus group discussions (FGD) in the second phase. The questionnaire is distributed to 309 respondents who are the specific decision-makers in this industry. Meanwhile, the FGD is conducted twice at different times with academics and practitioners, human resources and talent managers. This research used analytic hierarchy process as a tool for data processing.
Findings
This study provides current competency positions and future needs in the banking and FinTech industries in Indonesia where it found a lot of competence segregation. It also discovered three priority competencies for dealing with Industry 4.0, which included relating and networking, adapting and responding to change and entrepreneurship and commercial thinking.
Practical implications
This study is valuable for decision-makers and regulators; these results can be used to find new competencies and talents to develop existing human resources. Also, these results can be used as a basis for policy-making related to the Industrial Revolution 4.0.
Originality/value
This study provides new insights on talent mapping in the banking and FinTech industries as a strategic approach in the digitalization era. In addition, this research also adds knowledge related to Industry 4.0 as a result of industry developments in the digitalization era.
Apps and Unstructured Supplementary Service Data (USSD). The modeling uses a collaborative filtering approach with matrix factorization method and measure the model accuracy using Receiver Operating Characteristic / Area Under the Curve (ROC / AUC). The AUC value indicates the prediction quality of the model above prediction from random method. In addition, it was also concluded that the matrix factorization method provides advantages in resource efficiency. The
contribution of this research is to improve the customer experience, satisfaction, loyalty and engagement to Langit Musik.
In this research, we classify the feedback based on its category and sentiment. Several classification algorithms are used in opinion mining, two of them are Naive Bayes Classifier (NBC) and Support Vector Machine (SVM). This paper aims to classify feedback based on sentiments using NBC and SVM.
Understanding transaction system risk requires fundamental study on payments flow and bank behavior in various situations. Lehman Brother’s failure spread contagion impact in a short time indicates that financial markets have interdependent properties and connected to each other in a large network. Thus, overall system network approach becomes more important than a single bank.
Political conditions greatly affect economic stability including the banking and financial sectors. Presidential election is a major political event for a nation. This affected on community sentiment and financial market. However, the linkage between political events and topological changes is poorly understood.
This research presents an insight of the event driven dynamic network topology with banking transaction as a case study. We search for the banking transaction network topology dynamic driven by 2014 Indonesian presidential election event. We discover that banks are more engaged to others in larger value 3 days before the end of campaign period and less engaged to others in smaller value in the end of campaign period. Unique transaction activity between banks remain stable with low declination in the end of campaign period. This scenario provides the possibility to learn the banking transaction pattern and support the financial system stability supervision.
The purpose of this study is to predict the Indonesian composite stock price index by using macroeconomic variables as a reflection of economic condition and as a good signal to forecast stock prices. This research is using Inflation, Interest Rates, and Exchange Rates as the macroeconomic variables. This study uses secondary data from Bank Indonesia and Indonesian Statistics Center from December 2005 to November 2017. The prediction uses Artificial Neural Network (ANN) Backpropagation method.
The results gained the accuracy of 96,38% and mean-squared error of 0.0046 with the best time delay of 2 months before the predicted month. Based on the accuracy level and the error, macroeconomic variables (exchange rate, interest rate, inflation rate, and money supply M2) are the proper indicator to predict IDX Composite movement.
The main purpose of this research is content analysis, to obtain the goal, we need to extract the information as well as summarize the topic inside it. However, in order to analyze the content quickly, there are varies choice of tools with its specific output that creates challenges in the process. We use Naïve Bayes Sentiment Analysis based on time-series, specifically on daily basis and topic modeling based on Latent Dirichlet Allocation (LDA) to evaluate the sentiment of the topic as well as the model of the topics discussed.
The purpose of this research is to help both companies and individuals to map the public opinion towards certain topic by analyzing the sentiment of the text and create a topic model. Therefore, a real-time information for determining the consumer opinion become a crucial part. Twitter can serve the purpose as one source of real-time information from user-generated content. We pick Uber as the case study, viewed as one of the most favored transportation methods in most part of the world. Data collection period is from 10th February 2017 until 28th February 2017 with 1.048.576 tweets collected.
We explore the data pattern using two important data analytics methods classification and clustering procedure. Data analytics is the collection of activities to reveal unknown data pattern. Specifically, we use Artificial Neural Network classification and K-means clustering. The classification objective is to categorize different level of Human Development Index of cities or region in Indonesia based on Gross Domestic Product, Number of Population in Poverty, Number of Internet User, Number of Labors and Number of Population indicators data. We determined which city belongs to four categories of Human Development stated by UNDP standard. The clustering objective is to find the group characteristics between Human Development Index and Gross Domestic Product.
business that provide the way to optimize idle assets to generates new values for both asset owners and users. These business runs
sharing economy principle, where they provide two side services for individuals to earn money from their private idle assets and
for users who needs to use the assets. Until now, there are no specific model to describe the business elements in this kind of
economy. So, we will introduce the tools called Sharing Business Model Compass which can be used to describe the business elements in the sharing economy. For the case study, we analyse a creative hub’s business model using sharing business model compass. After being analysed, it is found that the effective way to charted a business model for businesses within the sharing economy is using sharing business model compass. The result is our research object fulfil all the six key elements of the sharing business model compass.
To support the government effort, we need a way to understand how people’s perception about tourism aspect in Indonesia. The easiest and cheapest way to see that is by extracting opinion from user generated reviews in a form of conversation among the users in social media such as Twitter. This paper proposes a method for extracting and summarizing of opinion or perception expressed by social media users. Our methods based on frequently appeared words and words relations among those dominant words. We call this method as Network Text Analysis, which is based on Social Network Analysis methodology.
As a case study, we conduct experiment against two tourism object aspect in Indonesia: Indoor and Outdoor tourist object. Specifically extracting user opinion regarding museum and nature destination from Twitter. The proposed methodology classifies topics from opinion data. Our method is fast and significantly accurate to summarize dominant topics in tourism industry when implemented in large-scale data.
to measure marketing intelligent effort.
This research performs sentiment analysis using naive bayes classifier classification method with TF-IDF weighting. We compare the sentiments towards of top-3 e-commerce sites visited companies, they are Bukalapak, Tokopedia and Elevenia. We use Twitter data for sentiment analysis because it's faster, cheaper and easier from both the customer and the researcher side. The purpose of this research is to find out how to process the huge customer sentiment Twitter to become useful information for the e-commerce company, and which of those top-3 e-commerce companies has the highest level of customer satisfaction. From the experiment results, it shows the method can be used to classify customer sentiments in social media Twitter automatically and Elevenia is the highest e-commerce with customer satisfaction.
Stock price movements are suitable with ANN requirement : it is a large data set because stock price is recorded up to every seconds, usually called high frequency data. The implementation of stock price prediction using ANN approach is quite new. The predictive model help investor in building stock portfolio and their decision making process. Buying some stocks in portfolio decrease diversified risk and increases the chance of higher return.
In this paper, we show how to generate prediction model using artificial neural network backpropagation of stock price and forming portfolio with predicted price that bring prediction of the portfolio with the smallest error. The data set we use is historical stock price data from ten different company stocks of infrastructure and consumer sector Indonesia Stock Exchage.
The results is for lower risk condition, ANN predictive model gives higher expected return than the return from real condition, while for higher risk, the return from the real condition is higher than the ANN predictive model.
be interpreted by using social network metrics; hence key role user or activity can be identified. . This paper shows the topology and centrality and engagement analysis of Telkom University network in social media. There are 6 metrics used to analyse this network. From those metrics we can obtain users behaviour in the network. This research shows that most of engaging topics are around visual presentation of Telkom University building and student communal activities. So far its user behaviour haven’t oriented toward insight gathering activities required by Telkom University to improve its activities. Based on this research we may suggest that to improve its content engagement, Telkom University may focus on topics
mentioned above, Telkom University physical facilities and student communal activities.
Many brands have their presence in oSNS as a part of their customer relationship management (CRM) effort. The social interactions formed in oSNS can be modeled using Social Network Analysis (SNA) methodology. In this paper, we compare two brand communities of head to head competitive product in the fast food industry, they are McDonald’s and Burger King. The SNA model constructs large-scale network, its size, reaching close to a million of nodes and edges. The result will give us insight about what is important in understanding the dynamic market beside the market size represented by the community conversations.
Kaskus, the biggest online forum in Indonesia is a common media for millions Indonesian to discuss about many things, including their music preference. Last.fm is a social network of music enthusiasts. We mine Last.fm conversational topics in Kaskus and model those data using Social Network Analysis methodology based on graph model. We implement community detection algorithms to identify group identification. We show that network interaction pattern among the users in online forum can be used to help music industry parties identify the dominant topics and/or dominant music fans group in Indonesia
Penelitian ini memanfaatkan big data dari media sosial Twitter yang diperoleh dari Twitter melalui API. Data tersebut kemudian diolah dengan metoda Social Network Analysis. Software yang digunakan untuk menghitung dan memvisualisasikan hasil analisis adalah Gephi. Penentuan aktor yang berperan dalam event JGTC 2013 dihitung berdasarkan centrality yang terdiri dari degree centrality, betweenness centrality, closeness centrality, dan eigenvector centrality. Sampel dalam penelitian ini adalah tweet yang berupa interaksi (terdapat mention, baik berupa reply maupun quote retweet) yang memuat kata ‘JGTC’ dan ‘#JGTC36’ pada 1 Desember 2013. Hasil penelitian pada event JGTC 2013 terdapat 7624 node (akun) yang terlibat dengan 7445 edge (interaksi) yang terjadi di network tersebut. Aktor (node) yang paling berpengaruh dalam network JGTC 2013 secara keseluruhan adalah raisa6690 yang merupakan bintang tamu pengisi acara pada event JGTC 2013.
The research was conducted by collecting all the tweets containing the conversation about KompasTV without limitation the location where the tweet was made to serve the population. For the sample, the data used is the tweet that contains a conversation about KompasTV replies, mentions, and retweets. This research is a descriptive study using SNA. Sizes studied are degree centrality, closeness centrality, betweeness centrality, eigenvector centrality and community detection.
From the results in 1025 nodes or account and 888 edges or interactions on the social conversation about KompasTV. There are eight accounts that become influencers in the network on the seven largest communities.
Social network analysis provides several metrics, which was built with no scalability in minds, thus it is computationally exhaustive. Some metrics such as centrality and community detections has exponential time and space complexity. With the availability of cheap but large-scale data, our challenge is how to measure social interactions based on those large-scale data. In this paper, we present our approach to reduce the computational complexity of social network analysis metrics based on graph compression method to solve real world brand awareness effort.
An efficient implementation of binary field arithmetic is an important prerequisite in Rijndael because Rijndael operations are performed using arithmetic operations in the underlying field. Two of the most common basis used in binary fields are polynomial basis and normal basis. In normal basis, raising to the 2th power is just a cyclic shift of the coordinates and therefore essentially free. One of the step in Rijndael algorithm is BytesSub which consists of inversion and affine transformation. In this paper we propose algorithms to speed up the encryption/decryption process in Rijndael. To be more precise we propose the use of storage efficient basis conversion from polynomial basis into normal basis and vice versa and the use of inversion algorithm in normal basis."