Skripsi

PREDIKSI HASIL TANGKAPAN IKAN YANG DISETORKAN KE PPS NIZAM ZACHMAN JAKARTA DENGAN XGBOOST

---

Prediction is the process of estimating future conditions using historical data as the basis for decision-making. This research develops a web-based fish catch prediction system using XGBoost algorithm based on time series with nonlinear regression method to predict fish production results submitted to the port. The data used is aggregate fish catch data from 12 fishing points during 2020– 2024. The development of the fish catch prediction model uses 2020–2024 data as test data totaling 576. Experiments were conducted with eight different scenarios for 8 training and testing models using aggregate dataset from 2020–2023 totaling 432 as test data and 2024 data as training data totaling 144. The results showed that the default XGBoost model with time series approach obtained the best model evaluation values with RMSE of 1,381,993.29, MAE of 713,287.39, and R² of 0.8262 with XGBoost default.

---

Availability

Detail Information

Series Title

-

Call Number

T1951092026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xiv, V-7 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

639.202 850 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
XGBOOST

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment