Prediksi (forecasting) merupakan alat bantu yang sangat penting dalam perencanaan yang efektif dan efisien khususnya dalam bidang ekonomi dan organisasi bisnis dalam setiap pengambilan keputusan yang sangat signifikan. Saat ini permasalahan yang paling sering terjadi dalam penerimaan siswa baru adalah tidak tercapainya kuota siswa yang mendaftar. Sehingga masih terdapat bangku kosong di banyak sekali sekolah. Metode Peramalan Autoregressive adalah salah satu metode dalam peramalan deret waktu. Deret Waktu / Time Series adalah suatu rangkaian atau seri dari nilai-nilai suatu variabel atau hasil observasi yang dicatat dalam jangka waktu yang berurutan. Pada Penelitian ini menggunakan metode Autoregressive untuk melakukan prediksi terhadap jumlah pendaftar pada periode yang akan mendatang. Hasil dari penelitian ini yaitu prediksi untuk tahun ajaran yang akan datang yaitu 97. Hasil pengujian fungsionalitas menggunakan Blackbox testing semua fungsionalitas dapat berjalan sesuai dengan perancangan. Hasil pengujian kepada pengguna sistem informasi menggunakan metode kuesioner didapatkan bahwa dari 15 kuesioner yang disebarkan kepada responden 13 orang atau 86,67%  menyatakan sangat setuju dan 2 orang atau 13,33% menyatakan setuju terhadap sistem informasi prediksi jumlah pendaftar siswa baru tersebut. Hasil pengujian menggunakan MAPE (Mean Absoute Percentage Error) sebesar 19,94%.Forecasting is a very important tool in effective and efficient planning, especially in the field of economics and business organization in every very significant decision making. Currently, the problem that most often occurs in the admission of new students is not achieving the quota of students who register. So there are still empty seats in many schools. Autoregressive Forecasting Method is one of the methods in time series forecasting. Time Series / Time Series is a series or series of the values of a variable or the results of observations that are recorded in successive periods of time. This study uses the Autoregressive method to predict the number of registrants in the future period. The results of this study are predictions for the upcoming academic year, namely 97. The results of testing functionality using Blackbox testing all functionality can run according to the design. The results of testing to information system users using the questionnaire method found that from 15 questionnaires distributed to respondents 13 people or 86.67% stated strongly agree and 2 people or 13.33% agreed with the information system predicting the number of new student registrants.The test results using MAPE (Mean Absoute Percentage Error) of 19.94%.

Nowadays, many netizens search for news via search engines with countless amounts of information, so it is increasingly difficult to determine when the number of news articles that appear changes very quickly and dynamically. Thus, it is necessary to process the extraction of news information to display the core information of the news. Problems arise, especially in Indonesian, which has a structure of various noun phrase entities with shallow parsing or grammatical induction. Named Entity Recognition (NER) has the opportunity to overcome this because it can extract news entities in depth, starting from proper nouns in text documents containing information search, machine translation, answering questions, and automatic summarization. This study aims to apply NER in Indonesian language news classification. This study uses Design-Based Research whose process includes (1) pre-implementation, (2) design, (3) implementation and revision, and finally, (4) reflection and evaluation. This application was developed on the platform python, streamlit, BeautifulSoup, gnews, and spacy library. The results of application accuracy testing have an F1-score value of 89.69% for all entities consisting of place, figure, day, date, and organization.

Prediction of student performance is an important thing for a university. This is because it can help a university to prevent or treat students who are at risk of failing in their studies early. This study aims to predict student performance at Duta Bangsa Surakarta University (UDB). The model used in this study is a logistic regression model. Logistic regression is a mathematical modelling method used to determine the relationship between a binary dependent variable and one or more independent variables. The results showed that the logistic regression model could be used to predict student performance with MAPE by 8%.  Keyword: Student Performace, Logistic Regression, UDB, MAPE

The objectives of this research is to implementation wavelet neuro fuzzy method to predict water level of Bengawan Solo river. The wavelet neuro fuzzy method is a model combination between discrete wavelet transformation, Artificial Neural Network (ANN) and fuzzy logic. Wavelet Neuro fuzzy modeling aims to reduce the weaknesses of each system, and combine existing advantages of each system, so the predicted result has a very small error value. Predicted when the flood is important because the predicted result can provide early warning information to the community around the river when the arrival of floods so as to reduce the risk of disaster and prepare for emergency response action. The data used in this research are high level of water level data obtained from AWLR Serenan post. The results of the wavelet neuro fuzzy method show the Mean Square error (MSE) forecast of 0.0613.

ABSTRAKKebutuhan akan energi listrik menjadi kebutuhan primer nasional. Dalam keberlangsungan proses produksi energi listrik pada pembangkitan -pembangkitan diperlukan energi listrik untuk pemakaian sendiri. Dalam penelitian ini dibangun sebuah aplikasi sistem cerdas untuk memprediksi energi listrik pemakaian sendiri di PT Indonesia Power sub unit PLTA Wonogiri. Pada penelitian ini menggunakan2 kelompok input, yaitu input FIS (Fuzzy Inference System) dan input pada NN (Neuro Fuzzy). Input data merupakan data produksi harian energi listrik di PLTA Wonogiri selama kurun waktu 2010 -2016. Variabel data yang digunakan dalam penelitian ini adalah data produksi listrik untuk pemakaian PLTA Wonogiri adalah energi listrik yang dihasilkan PLTA Wonogiri dengan satuan KwH (f), elevasi muka air waduk dengan satuan meter (a1) dan debit air yang masuk ke turbin dengan satuan /detik (a2). Output yang diperoleh adalah pusat centroid (m), derajat keanggotaan (mf), bobot (w) dan konsekuen parameter ( c ). Dari hasil pengujian diperoleh keluaran dengan performansi yang optimal pada saat Fuzzy C Means 2 kelas dengan parameter laju pembelajaran 0.4, momentum 0.6 dengan bessar Mean Percentage Error 0.377970875.Kata kunci: prediksi, pemakaian sendiri, energi listrik, fuzzy inference system, neuro fuzzy. ABSTRACT The need for electrical energy becomes the national primary need. In the continuity of the production process of electrical energy in the generation of electricity generation required for own use. In this study built an intelligent system application to predict the power of electricity own use in PT Indonesia Power sub unit Wonogiri power plant. In this research use 2 input group, that is input of FIS (Fuzzy Inference System) and input on NN (Neuro Fuzzy). Data input is daily production data of electric energy at Wonogiri hydroelectric during 2010 -2016 period. Variable of data used in this research is electricity production data for Wonogiri hydropower usage is electric energy generated Wonogiri hydro power with unit KwH (f), water level elevation Reservoir with meter unit (a1) and water discharge entering turbine with unit / second (a2). The output obtained is centroid center (m), degree of membership (mf), weight (w) and consequent parameter (c). From the test results obtained output with optimal performance in