Test Potensi Akademik (TPA) memiliki peran penting untuk mengukur dan menemukan SDM yang berkualitas berdasarkan kemampuan seseorang di bidang keilmuan atau akademis. Tes ini sangat dibutuhkan dalam penerimaan mahasiswa baru maupun memasuki dunia kerja. Dengan demikian siswa tingkat SMA/sederajat perlu mempersiapkan diri untuk menghadapi tes ini. Sebagai bentuk dukungan kepada peningkatan potensi siswa maka Tim Pengabdian Kepada Masyarakat (PKM) dari dosen Jurusan Statistika, Fakultsas Sains Terapan, Institut Sains & Teknologi AKPRIND Yogyakarta mengadakan pelatihan persiapan menghadapi tes TPA kepada siswa SMA Muhammadiyah 1 Prambanan. Materi yang diberikan adalah tentang pengetahuan peran dan fungsi TPA serta pengerjaan berbagai jenis soal TPA. Berdasarkan hasil keseluruhan evaluasi, dapat diketahui bahwa target utama dari pelaksanaan pelatihan telah tercapai. Peserta lebih memahami tujuan dan jenis-jenis TPA, serta mampu mengerjakan beberapa soal TPA dengan baik.

Consumers have many options for shopping their daily needs, both in modern and traditional markets, or retail which especially minimarkets. Thus the competition among minimarket is also very high. Each minimarket has different marketing strategies, because the characteristics of consumers in shopping also vary. Marketing strategy need information from various aspects from consumers, competitors, and products are needed. This study analyze factors that influence the interest of consumers who shop at minimarket. Factor studied is in terms of consumers, both characteristics and location of residence. The data used is the primary data by conducting interviews survey on consumers in the Ngaglik District, Sleman Regency, Special Region of Yogyakarta. The minimarket sample is Indomaret. The method analysis are logistic regression and Classification and Regression Trees (CART). The result indicate that the significant factors that influence to shopping interest with logistic regression method are gender, monthly average expenditure, and location. While the factor plays an important role in CART is also the location. The CART, as a nonparametric method that doesn't have a certain distribution assumption, has higher classification accuracy. This is indicated by the percentage value of classification accuracy in CART is 90%, while logistic regression is 88%.

Hidden Markov model is a development of the Markov chain where the state cannot be observed directly (hidden), but can only be observed, a set of other observations and combination of fuzzy logic and Markov chain to predict Rupiah exchange rate against the Dollar. The exchange rate of purchasing and exchange rate of saling is divided into four states, namely down large, down small, small rise, and large rise are symbolized respectively S1, S2, S3, and S4. Probability of sequences of observation for 3 days later is computed by forwarding and Backward Algorithm, determine the hidden state sequence using the viterbi algorithm and estimate the HMM parameters using the Baum Welch algorithm. The MAPE result exchange rate of purchase of FTS-Markov Chain is 1,355% and the exchange rate of sale of FTS-Markov Chain is 1,317%. The sequences of observation which optimized within exchange rate of  purchase is X* = {S3,S3,S3}, within exchange rate of sale is also X* = {S3,S3,S3}. Keywords: Exchange rate, FTS-Markov Chain, Hidden Markov Model

East Java Province has an uneven welfare condition. The uneven welfare conditions are indicated by a large number of poor people in East Java and the rate of economic growth which has decreased in 2020, reaching -2.39% due to the impact of the pandemic. Welfare can be measured through several indicators, while the indicators used to classify districts and cities in East Java among others include population density, labor force, labor force participation rate, and open unemployment rate. Thus, to find out the grouping of regencies and cities in East Java Province based on the level of welfare, grouping was carried out using the K-Means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) methods. For each of the two methods, distance calculations are performed using the Euclidean and Manhattan distances. Each distance was tested for validity using the Davies-Bouldin Index (DBI), C-Index, and Dunn Index. This study concludes that the best method is the DBSCAN method using Manhattan distance with MinPts = 2 and eps = 4 which has the smallest DBI value of 0.284, with 2 clusters formed and 5 noise. Cluster 1 consists of 26 regencies, cluster 2 consists of 7 cities, and noise consist of 5 regencies and cities. Keywords: Welfare, K-Means, DBSCAN, Euclidean Distance, Manhattan Distance.