Data Mining - Definisi, Contoh dan Implementasi

• Definisi Data Mining

a. Data mining adalah metode untuk mengekplorasi informasi dan data baru dari banyak informasi di pusat distribusi informasi, memanfaatkan kekuatan otak buatan (Kecerdasan Buatan), pengukuran dan aritmatika. Data mining merupakan inovasi yang diandalkan untuk menghubungkan korespondensi antara informasi dan kliennya. (Jollyta, Ramdhan, & Zarlis, 2020)

b. Data mining adalah tahap kajian berbagai informasi yang sebagian besar berukuran sangat besar untuk mendapatkan hubungan antara informasi dan merangkumnya dalam struktur yang mudah dimanfaatkan(Han, 2006). (Prasetyowati, 2017)

c. Data mining diinterpretasikan menjadi sekelompok strategi yang dipakai secara impulsif untuk menyelidiki sepenuhnya dan memperkenalkan hubungan permukaan yang kompleks pada koleksi informasi yang sangat banyak. (Siregar & Puspabhuana, 2017)

d. We characterize information mining as the most common way of tracking constructions of interest with respect to information. Construction may require many structures, including a set of rules, a chart or organization, a tree, one or more conditions, and so on. (Roiger, 2017)

e. Data mining is the most common way of finding significant new connections, examples and patterns by filtering through a lot of information put away in warehouses, involving design acknowledgment advancements as well as factual and numerical procedures. (Larose & Larose, 2014)

f. Data mining or information disclosure in data sets (KDD) is an assortment of investigation strategies in view of cutting edge logical techniques and instruments for dealing with a lot of data. (Gupta, 2012)

                Jadi Data mining adalah sebuah metode untuk menemukan koneksi,contoh dan pola baru yang tersimpan di pusat distribusi informasi, dimana informasi yang besar dan data baru yang diekplorasi tersebut mendapatkan hubungan antara informasi dan kliennya sehingga metode ini memerlukan banyak struktur untuk merangkumnya agar mudah dimanfaatkan.

• Contoh Implementasi Data Mining

- Pada bidang bisnis dan penjualan

            Implementasi Data Mining Menggunakan Algoritma Apriori pada Apotek menjadi salah satu contoh implementasi data mining dalam bidang bisnis dan penjualan, dimana kegunaanya adalah terletak pada penentuan campuran barang yang sering dibeli konsumen dengan menggunakan metode assosiasi dengan algoritma apriori yang merupakan salah satu contoh metode data mining.

-Pada sektor pendidikan

            Implementasi Data Mining Menggunakan Algoritme Naive Bayes Classifier dan C4.5 untuk Memprediksi Kelulusan Mahasiswa menjadi salah satu contoh implementasi data mining dibidang pendidikan dimana banyaknya mahasiswa tidak lulus tepat pada waktunya. Ini menimbulkan kekhawatiran program studi dikarenakan salah satu tanda tercapainya program studi harus terlihat dari lamanya studi mahasiswa.

- Pada bidang kesehatan

            Implementasi Data Mining Untuk Memprediksi Penyakit Jantung Mengunakan Metode Naive Bayes menjadi salah satu contoh implementasi data mining dibidang kesehatan dimana pada dasarnya penyakit harus terlihat dari kehadirannya secara langsung. Bagaimanapun, karena ketiadaan informasi, banyak orang mengakuinya merasa tidak sadar akan datangnya penyakit tersebut. Kedepannya, persoalan ini memicu kekhawatiran untuk masalah kesehatan. Akibatnya, penelitian ini diarahkan untuk menurunkan angka kematian sejak awal.

• Rangkuman Jurnal Implementasi Data Mining

- Journal Title : Implementation of Data Mining To Predict Period of Students Study Using Naive Bayes Algorithm

- Name Journal : International Journal of Engineering and Emerging Technology

- Writer : Ida Bagus Adisimakrisna Peling, I Nyoman Arnawan, I Putu Arich Arthawan, dan IGN Janardana

- Volume : Vol. 2, No. 1, January—June 2017

- Year : 2017

- E-ISSN: 2579-597X

I. Background

            One of the problems that is still a matter of discussion regarding student failure is that students graduate not on time. Students who graduate not on time are students who cannot complete their studies in accordance with the allotted time. The presence of postgraduate students who are not on time certainly causes problems and has the potential to drop out which affects the quality of education and accreditation.

            In light of the abovementioned, it needs a framework that can foresee the graduation of understudies through figuring out how to assess results. Idealness graduate understudies can do with information mining methods to find designs that have passed the graduation which is then utilized as the reason for anticipating graduation in the following year.

II. Purpose of Journal Writing

                 The reason for this assessment is implementing data mining to predict period of students study using the naive bayes algorithm to find the pattern of graduation that has been passed which is then used as the basis for predicting graduation in the following year.

III. Research Methodology

Below are the research methods contained in the journal:

A. Data Mining

            Data Mining is the most common way of separating data from an exceptionally enormous arrangement of information using calculations and withdrawal strategies in the field of measurements, AI and data set administration frameworks.

B. Naive Bayes

            Naive Bayes is a straightforward probabilistic classifier that work out a bunch of probabilities by adding the recurrence and worth mix of given dataset.

IV. Research result and Discussion

              The results obtained by collecting data with various attributes where for the study period are divided into two categories, namely on time and not on time. After the data is obtained, the data is then processed.

            From the aftereffects of the computation of exactness and blunder that has been done is gotten from the calculation naive bayes precision of 80% and mistake of 20%. There were additionally trial of 80 understudy information with information testing of 10%, 20% and 30% of the all out information to decide the exactness of Naive Bayes.

            From the expectation results acquired additionally other data that understudies who come from the Path PMDK graduated on schedule as much as 40%, other band relax of 26,7%, and the test channel graduated on schedule of 13.3%. Can be broke down the outcomes that understudies who go through the way PMDK tends to pass more rapidly than understudies through the other way and the way of the channel test.

V. Conclusion

            This review shows that Nave Bayes can accurately arrange information testing. From the examination that has been done can be finished up from the aftereffects of testing calculation Naive Bayes has a normal precision of 86.16% and mistake of 13,84%. With the quantity of tests of 15 understudies utilized the test information utilizing guileless bayes strategy acquired the outcome that understudies who will graduate on time added up to 12 understudies or around 80% of the example while the understudy who will graduate isn't on time added up to 3 understudies or around 20%.

Strengths and Weaknesses

             The advantage is that the appropriate analysis results are equipped with supporting data. the only drawback is the lack of in-depth literature study.

Sumber Referensi

Gupta, G. K. (2012). INTRODUCTION TO DATA MINING WITH CASE STUDIES. Delhi: Asoke K. Ghost.

Jollyta, D., Ramdhan, W., & Zarlis, M. (2020). KONSEP DATA MINING DAN PENERAPAN. Yogyakarta: Deepublish.

Larose, D. T., & Larose, C. D. (2014). Discovering Knowledge in Data: An Introduction to Data Mining. Hoboken: John Wiley & Sons, Inc.

Prasetyowati, E. (2017). DATA MINING. Pamekasan: Duta Media Publishing.

Roiger, R. J. (2017). DATA MINING A Tutorial-Based Primer. Taylor & Francis Group.

Siregar, A. M., & Puspabhuana, A. (2017). DATA MINING : Pengolahan Data Menjadi Informasi dengan RapidMiner. CV Kekata Group.

Wijayanti, A. (2017). Analisis Hasil Implementasi Data Mining Menggunakan Algoritma Apriori pada Apotek. Jurnal Edukasi dan Penelitian Informatika (JEPIN), 3.

Etriyanti, E., Syamsuar, D., & Kunang, Y. N. (2020). Implementasi Data Mining Menggunakan Algoritme Naive Bayes Classifier dan C4.5 untuk Memprediksi Kelulusan Mahasiswa. Telematika, 56-67 .

Ade, R., Susianto, Y., & Rahman, N. (2019). Implementasi Data Mining Untuk Memprediksi Penyakit Jantung Mengunakan Metode Naive Bayes . Journal of Innovation Information Technology and Application, 25-34 .

Peling, I. B., & dkk. (2017). Implementation of Data Mining To Predict Period of Students Study Using Naive Bayes Algorithm. International Journal of Engineering and Emerging Technology, Vol. 2, 53-57.