Prediction of Fishermens Income with Model Flexible Approach in Karanggongso Fishermen Community, Trenggalek Regency
Agus Dwi Sulistyono (a), Pudji Purwanti (a), Edi Susilo (a), Niken H. Wardani (a)

a) 1 Department of Socio-Economy Fisheries and Marine, Faculty of Fisheries and Marine Sciences, Universitas Brawijaya
*agusdwistat[at]ub.ac.id

Abstract

Due to the enactment of Presidential Regulation (Perpres) Number 44 of 2016, there are opportunities for fishermen to increase their productivity. The role of the marine economy and the synergy of national marine development is the utilization of marine resources for economic development and the welfare of fishermen and coastal communities. The contribution of Fisheries Quarterly at the current 2014-2018 prices to the National GDP shows that contributions have increased from an average of 2.32% in 2014 to 2.60% in 2018. This shows an increase in value that reflects an increase in the income of the fisheries sector on average. However, in 2020, the threat of the Covid19 pandemic emerged, which hit all sectors of the economy, including the fisheries sector. Many communities, especially coastal fishing communities, are complaining about economic hardship. Income has fallen dramatically because peoples purchasing power has fallen significantly. Based on these problems, this research was conducted to build a fishermen income prediction model with a machine learning approach, where this research took a case study on fishermen in Karanggongso District Trenggalek. This research was conducted by surveying 50 fishing households. The process of data analysis was done by using multiple linear regression analysis and flexible modeling with a machine learning approach. Based on the results of multiple linear regression analysis, prediction models were obtained with an accuracy level of R2 = 70.1%, and MSE = 1.086 x 1018 with the boat price variable was the most dominant influence on fishermen income. While based on the results of modeling with a flexible model, prediction models were obtained with an accuracy level of R2 = 85.2% and MSE = 3.308 x 1014. From this research, it was proven that the flexible model with a machine learning approach had a higher level of accuracy than the linear regression model. Also, the flexible model obtained the effect of nonlinear variables on the number of cool boxes and the age of the fishing tools.

Keywords: flexible model, machine learning, prediction, fishermens income

Topic: FISHERIES AND MARINE RESOURCES TECHNOLOGY