Proses pengerjaan machine learning pada umumnya meliputi uji coba berbagai model terhadap dataset dengan memilih model dengan performa terbaik. Untuk mendapatkan hasil prediksi data yang akurat, diperlukan tidak hanya model machine learning yang tepat, tetapi juga hyperparameter (parameter yang mengatur proses pembelajaran mesin) yang tepat pula yang dikenal dengan istilah hyperparameter tuning. Menentukan kombinasi yang tepat antara model dan hyperparameter seringkali menjadi tantangan.

Data wrangling sometimes could become very tedious. No matter what language do you prefer: R, python, or even SQL, the process of preprocessing your dataset is generally very time consuming. But, this is not the case if you know how to properly use packages included in tidyverse.

Some data that we obtain from the internet are gained as a raw, means that there are no modifications done to the data except placing it in the right column or row. Even if that’s a good thing, sometimes you have to treat and change the template of the data to be as friendly to reach our objective as possible.