The development of data needs is a door that clearly connects the world of Higher Education and Industry. Students especially in the Statistics Study Program have demands to be able to understand the actual use of existing data. Through the Machine Learning Statistics course, the Statistics Study Program FMIPA UNY held a practitioner's lecture by inviting one of the professional Data Scientists in Indonesia, namely Nur Chamid, S.Sc.. He is a Data Scientist at PT. Astra International Tbk and alumni of the Mathematics Study Program, FMIPA UNY.

This practitioner lecture runs as many as 3 lecture sessions, namely on April 9th, 16th, and 23rd 2022. The topics discussed during the first lecture session discussed the topics of Bagging, Boasting and Random Forrest. This topic is related to ensemble techniques, the goal is none other than to increase accuracy or minimize errors from the analysis performed. Even though there are model improvement options, this ensemble technique is not free from drawbacks in the form of more time consumption and greater storage usage. Then in the second lecture session raised the topic of Cluster Analysis. Cluster analysis is a multivariate technique that aims to group objects based on their characteristics. Objects can be products (goods and services), objects (plants or others), and people (respondents, consumers or others). The object will be classified into one or more clusters (groups) so that objects in one cluster will have similarities to one another. The third lecture session on 23 April 2022 discussed Feature Selection and Dimensional Reduction. Feature Selection and Dimensional Reduction are data preparation techniques before being analyzed which aims to select features that have a strong relationship with the desired analysis results.

The target for this activity were Statistics students for class G 2019 and G 2020. During the three sessions, an average of 50 students attended and participated. It is hoped that by holding this practitioner activity, students will be more aware that there are other statistical models that need to be understood as a basis for accurate data analysis.