Hasil Pencarian  ::  Simpan CSV :: Kembali

"ABSTRAKSebagai proses alamiah dalam mencapai titik ekuilibrium, perkembangan ekonomi digital akan selalu diikuti oleh peningkatan risiko keamanan cyber. Penelitian ini membahas analisis big data percakapan media sosial Twitter dengan tipe data yang tidak terstruktur untuk memprediksi risiko cyber berupa keberhasilan serangan exploit terhadap kerentanan sistem informasi yang dipublikasikan pada situs kerentanan global cvedetails.com common vulnerabilities and exposures CVE . Penelitian ini mengeksplorasi aspek kualitatif dan kuantitatif atas data yang bersumber dari twitter dan CVE menggunakan metode pemodelan algoritmik statistical machine learning. Prediksi dilakukan dengan membandingkan beberapa model klasifikasi yang dipilih dari sepuluh algoritma yang paling banyak digunakan dalam data mining berdasarkan survey yang dilakukan oleh IEEE pada International Conference on Data Mining tahun 2006. Hasil prediksi terbaik dihasilkan melalui model algoritma Artificial Neural Networks dengan tingkat akurasi 96,73 . Model prediksi dapat dimanfaatkan oleh perusahaan asuransi dengan produk perlindungan risiko cyber untuk mengurangi potensi penyebaran klaim terjadinya risiko. Model juga dapat dimanfaatkan oleh perusahaan umum untuk melakukan mitigasi risiko cyber secara efektif dan efisien dengan menghindari situasi false-negatives error dalam pengelolaan risiko.

---

ABSTRACTAs a natural process in achieving equilibrium state, digital economic progress will always be followed by the increase of cyber security risk exposure. This research is focusing on unstructured Twitter social media big data analytics to predict cyber risks event in terms of successful attack on exploit based software vulnerability published in global vulnerability information websites cvedetails.com common vulnerabilities and exposures CVE . This research explores qualitative and quantitative aspect of data extracted from Twitter and CVE using statistical machine learning algorithmic modeling method. Prediction result obtained by comparing and selecting classification model from several statistical machine learning algorithm based on top ten algorithms in data mining survey produced by IEEE in 2006 International Conference on Data Mining. The best prediction results provided through Artificial Neural Networks algorithm with 96,73 accuracy rate. This prediction model offers advantages for insurance company with cyber liability product by reducing claim spread probability over cyber risk loss event. Prediction model can also be beneficial for company in general by providing an effective and efficient way to mitigate cyber risks through false negatives error avoidance in risk management."

"Access to big data, the “new commodity” for the 21st century economies, and its uses and potential abuses, has both conceptual and methodological impacts for the field of comparative and international education. This book examines, from a comparative perspective, the impact of the movement from the so-called knowledge-based economy towards the Intelligent Economy, which is premised upon the application of knowledge. Knowledge, the central component of the knowledge-based economy, is becoming less important in an era that is projected to be dominated and defined by the integration of complex technologies under the banner of the fourth industrial revolution. In this new era that blends the physical with the cyber-physical, the rise of education intelligence means that clients including countries, organizations, and other stakeholders are equipped with cutting-edge data in the form of predicative analytics, and knowledge about global educational predictions of future outcomes and trends. In this sense, this timely volume links the advent of this new technological revolution to the world of governance and policy formulation in education in order to open a broader discussion about the systemic and human implications for education of the emerging intelligent economy. By providing a unique comparative perspective on the Educational Intelligent economy, this book will prove invaluable for researchers and scholars in the areas of comparative education, artificial intelligence and educational policy."

"Prediksi klaim merupakan proses penting dalam industri asuransi karena perusahaan asuransi dapat menyiapkan jenis polis asuransi yang tepat untuk masing-masing pemegang polis potensial. Frekuensi prediksi klaim dewasa ini kian meningkat. Sehingga data prediksi klaim yang memiliki volume besar ini disebut big data, baik dari segi jumlah fitur maupun jumlah data pemegang polis. Salah satu alternatif solusi perusahaan asuransi untuk melihat pemegang polis melakukan klaim atau tidak, bisa menggunakan machine learning yang teruji dapat digunakan untuk klasifikasi dan prediksi. Salah satu metode machine learning untuk mengurangi jumlah fitur adalah dengan proses seleksi fitur, yaitu mencari urutan fitur berdasarkan tingkat pentingnya fitur. Metode seleksi fitur yang digunakan adalah Gram-Schmidt Orthogonalization. Metode ini sebelumnya digunakan untuk data tidak terstruktur namun pada penelitian ini diuji pada data terstruktur bervolume besar. Untuk menguji urutan fitur yang diperoleh dari proses seleksi fitur, digunakan Support Vector Machine karena termasuk metode machine learning yang popular untuk klasifikasi. Berdasarkan hasil simulasi, urutan yang diperoleh dari proses Gram-Schmidt Orthogonalization relatif konsisten. Selanjutnya, dapat diketahui fitur-fitur yang paling berpengaruh untuk menentukan pemegang polis klaim atau tidak. Simulasi juga menunjukkan bahwa hanya dengan menggunakan sekitar 26 % fitur, akurasi yang dihasilkan sebanding dengan menggunakan semua fitur.

---

Claim prediction is an important process in the insurance industry because insurance companies can prepare the right type of insurance policy for each potential policyholder. The frequency of today`s claim predictions is increasing. So that claim prediction data has a large volume called big data, both in terms of the number of features and the number of policyholders. One alternative solution for insurance companies to see whether policyholders claim or not, we can use machine learning that is proven to be used for classification and prediction. One of the machine learning methods to reduce the number of features is the feature selection process, which is to search for sequences of features based on their importance feature. The feature selection method used is Gram-Schmidt Orthogonalization. This method was previously used for unstructured data, but in this research is tested on large volume structured data. Support Vector Machine is used to test the ordered features obtained from the feature selection process because it is a popular machine learning method for classification. Based on a result, the ordered features obtained from the Gram-Schmidt Orthogonalization process is relatively stable. After that, it can also be seen the most important features to determine policyholders claim or not. The simulation also shows that using only about 26 % features, the resulting accuracy is comparable to using all features."

"Pemanfaatan Palm Oil Biodiesel mulai berkembang sejalan dengan pelaksanaan kebijakan mandatori BBN dari 2.805 Ribu kL di 2013 menjadi 4.706 Ribu kL pada 2018. Keberhasilan transisi energi melibatkan sektor keuangan dan keseimbangan tiga dimensi energi yaitu keamanan, kesetaraan, dan keberlanjutan lingkungan. Diperlukan teknologi Big Data untuk menangani berbagai variasi dan komparasi data yang disesuaikan dengan parameter Keuangan dan Trilemma Energi pada penerapan Palm Oil Biodiesel. Tahapan penelitian ini melalui proses pengelompokan data numerik dan kategorik yang kemudian melewati tahap training dan pengujian data. Output nya berupa hasil studi Big Data pada risiko kebijakan energi dalam penerapan Palm Oil Biodiesel. Simulasi tersebut dilakukan dengan menggunakan pemprograman Python. Badan Usaha BBN (SMAR.JK, TBLA.JK, dan CEKA.JK) menghasilkan Stock Return sebesar 28%. Kovarians terkecil terjadi antara saham SMAR.JK dan TBLA.JK, dengan korelasi dari ketiga saham tergolong rendah. Sharpe Ratio ketiganya menghasilkan 0,83-0,84. Skenario penerapan Biodiesel ini memberikan dampak progresif terhadap pertumbuhan energy equity dan energy security namun terjadi arah penurunan pada aspek environmental sustainability dengan penjabaran tahun 2020 aspek energy equity; environmental sustainability; energy security [0,72; 0;65; 0,79] diproyeksikan tahun 2023 [0,83; 0,53; 0,83]. Dalam penerapan kebijakan energi dalam penerapan Palm Oil Biodiesel tersebut terdapat risiko yang perlu diperhatinkan terhadap pelaksanaannya. Pada krisis tahun 2008 yang menunjukkan ketidaksbilan pada sektor keuangan. Dari Grafik 4.1. Total Badan Usaha BBN Stock Return menunjukkan SMAR.JK mengalami krisis paling berat. TBLA.JK paling stabil dan CEKA.JK tidak mengalami penurunan yang signifikan. Ketika DMO (Domestic Market Obligation) Palm Oil tidak terpenuhi maka biaya lingkungan tidak tercapai

---

The utilization of palm oil biodiesel begins to develop rapidly in conjunction with the implementation of the biofuel mandatory policy, from 2,805 thousand kL in 2013 to 4,706 thousand kL in 2018. Achieving the transition involves the financial sector and the balance of three energy dimensions: security, equity, and environmental sustainability. Big Data Technology is required to handle numerous data variations and comparisons adjusted with the Finance and Energy Trilemma parameter in palm oil biodiesel implementation. This research begins with grouping numerical and categorical data and then continues to data training and data testing. The output will be the results of Big Data analysis on the risks of energy policy in palm oil biofuel implementation. Python software is used to perform the simulation. Biofuel companies (SMARJK, TBLA.JK, and CEKA.JK) yield 28% stock return. The smallest covariance exists between the stocks of SMAR.JK and TBLA.JK, while the correlation between the three companies’ stocks is considered low. The Sharpe Ratio of the three ranges from 0.83 to 0.84. This biodiesel implementation scenario contributes a progressive impact on the growth of energy equity and energy security but lowers environmental sustainability. The value of energy equity, environmental sustainability, and energy security in 2020 is expressed consecutively as [0.72, 0.65, 0.79], which is projected to 2023 with the value expressed as [0.83, 0.53, 0.83]. Risks in conducting the energy policies of palm oil biodiesel should be considered. The crisis that occurred in 2008 displayed instability in the financial sector. Based on Chart 4.1. Total Stock Return of Biodiesel Companies, SMAR.JK suffered from the crisis the most. TBLA.JK was the most secure, and CEKA.JK did not experience a significant decline. If the DMO (Domestic Market Obligation) of palm oil is not met, the environmental cost will not be attained."