Ibu Kota memiliki peran penting dalam menggambarkan seberapa besar kekuatan politik, kultural, dan ekonomi suatu negara. Apabila Ibu Kota suatu negara memiliki banyak masalah yang tidak terselesaikan, permasalahan tersebut dapat menjadi faktor–faktor yang memengaruhi suatu negara memindahkan Ibu Kotanya. Setelah ditelusuri, terdapat banyak negara yang pernah memindahkan Ibu Kotanya termasuk Indonesia. Tujuan dari penelitian ini adalah untuk membentuk model dan menganalisis faktor–faktor yang memengaruhi negara–negara di dunia memindahkan Ibu Kota dengan data yang mengandung masalah: 1. Outlier, 2. Missing values, 3. Data tak seimbang, 4. Multikolinearitas. Jika data mengandung masalah, maka model yang terbentuk menjadi tidak representatif dan sulit untuk diinterpretasikan. Sehingga diperlukan metode yang dapat digunakan untuk menangani 4 (empat) masalah tersebut, yaitu berturut-turut: 1. Quantile–Based Flooring Capping, 2. K–Nearest Neighbor, 3. Adaptive Synthetic (ADASYN), dan 4. Menerapkan model Least Absolute Shrinkage and Selection Operator (LASSO) pada regresi logistik. Hasilnya menunjukkan bahwa faktor yang memengaruhi suatu negara memindahkan Ibu Kotanya adalah ukuran populasi di Ibu Kota, populasi negara, luas area (km2), Usia Negara, sistem pemerintahan, Income Category, dan Sedangkan faktor yang tidak masuk ke dalam model yaitu Gross Domestic Product (GDP), Logistic Performance Index (LPI) Score, Regulatory Quality Index, dan E–Government Development Index adalah prediktor yang mengalami multikolinearitas, sehingga model LASSO pada regresi logistik berhasil menyusutkan prediktor tersebut menjadi 0. Adapun model akhir dari Least Absolute Shrinkage and Selection Operator (LASSO) pada regresi logistik yang diperoleh adalah g(x) = 0,3399 – 0,8019 POP_CITY + 3,5925 POP_COUNTRY + 0,3406 AREA – 0,0156 AIRPOL + 0,0679 GEI + 0,8351 PS_AVT – 0,5682 GOV_EFFECT – 1,8643 AGE – 0,7043 SYSTEM_A – 1,4408 SYSTEM_B – 0,7036 INCOME_A – 0,5272 INCOME_B – 3,7404 INCOME_C – 0,9489 ARCHIPELAGO.

---

The capital city plays an important role in portraying how much political, cultural and economic power a country has. If the capital city has many unresolved problems, these problems can become factors that influence the country to move its capital city. After being traced, there are many countries that have moved their capital cities, including Indonesia. The purpose of this study is to model and analyze the factors that influence countries in the world to move its capital city with data containing problems: 1. Outliers, 2. Missing values, 3. Imbalanced data, 4. Multicollinearity. If the data contains these problems, the model formed becomes unrepresentative and difficult to interpret. Therefore, the methods that can be used to handle these 4 (four) problems, respectively: 1. Quantile-Based Flooring Capping, 2. K-Nearest Neighbor, 3. Adaptive Synthetic (ADASYN), and 4. Applying the Least Absolute Shrinkage and Selection Operator (LASSO) model in logistic regression. The results showed that the factors that influence a country to move its capital city are population size in the capital city, country population, area (km2), air pollution level (mg/m3), Global Entrepreneurship Index (GEI), Political Stability and No Violence/Terrorism Index, Government Effectiveness Index, Country Age, government system, Income Category, and whether a country is an archipelago or not. While the factors that did not enter the model, namely the Gross Domestic Product (GDP), Logistic Performance Index (LPI) Score, Regulatory Quality Index, and E-Government Development Index were predictors that experienced multicollinearity, so the LASSO model in logistic regression successfully shrinks these predictors to 0. The final Least Absolute Shrinkage and Selection Operator (LASSO) model in logistic regression obtained is g(x) = 0,3399 – 0,8019 POP_CITY + 3,5925 POP_COUNTRY + 0,3406 AREA – 0,0156 AIRPOL + 0,0679 GEI + 0,8351 PS_AVT – 0,5682 GOV_EFFECT – 1,8643 AGE – 0,7043 SYSTEM_A – 1,4408 SYSTEM_B – 0,7036 INCOME_A – 0,5272 INCOME_B – 3,740