Implementation of Gaussian Process Regression in Estimating Motor Vehicle Insurance Claims Reserves

This study aims to calculate the allowance for losses by applying Gaussian Process regression to estimate future claims. Modeling is done on motor vehicle insurance data. The data used in this study are historical data on PT XYZ's motor vehicle insurance business line during 2017 and 2019 (January 2017 to December 2019). Data analysis will be carried out on the 2017 - 2019 data to obtain an estimate of the claim reserves in the following year, namely 2018 - 2020. This study uses the Chain Ladder method which is the most popular loss reserving method in theory and practice. The estimation results show that the Gaussian Process Regression method is very flexible and can be applied without much adjustment. These results were also compared with the Chain Ladder method. Estimated claim reserves for PT XYZ's motor vehicle business line using the chain-ladder method, the company must provide funds for 2017 of 8,997,979,222 IDR in 2018 16,194,503,605 IDR in 2019 amounting to Rp. 1,719,764,520 for backup. Meanwhile, by using the Bayessian Gaussian Process method, the company must provide funds for 2017 of 9,060,965,077 IDR in 2018 amounting to 16,307,865,130 IDR, and in 2019 1,731,802,871 IDR for backup. The more conservative Bayessian Gaussian Process method. Motor vehicle insurance data has a short development time (claims occur) so that it is included in the short-tail type of business.

Organic and Inorganic N-Fertilizer Management for Rice under Rice-Wheat Cropping System

Nitrogen (N) is the most important crop nutrient for improving crop productivity in rice-wheat cropping system. The continuous use of chemical fertilizer would lead gradual to decline of organic matter content and native N status in the soil, and decrease productivity in rice-wheat system. Alternatives have to be found out to improve the productive capacity of rice soils. Therefore, the present research was designed to investigate the application effect of six different organic N sources (OS) applied alone and in various combinations (75: 25, 50: 50 and 25: 75 %) with urea (U) on rice hybrid (Oryza sativa L., cv. Pukhraj), and their residual effects on the yield and yield components of subsequent wheat (Triticum aestivum L., cv. Siren). The field experiment was carried out on farmer’s field at Butkhela (Malakand) during 2011-13. The results revealed that the rest (N applied plots) showed better growth, higher yield and profitability than control (N not applied) in both crops. The inorganic N fertilizer (urea) was more beneficial in terms of better growth, yield, yield components, and profitability in case of current rice crop but had the less residual soil residual N after rice harvest that showed negative impact on the yield, yield components and profitability of subsequent wheat crop when compared with OS. Among the six OS used [three each from animal manures (AM) and three crop residues (CR)], poultry manure (PM) improved growth, yield components, biological (16331 kg ha-1) and grain yields (8459 kg ha-1), rice grains N contents (22%), soil N content (726 mg kg-1) after rice harvest, and had the highest profitability (192,000 PKR) than other OS. Results revealed that application of wheat straw resulted in the lowest biological (13020 and 7916 kg ha-1) and grain yields (6200 and 3219 kg ha-1) in both crops respectively and also had the less profitability (28,000 and 39,000 PKR) under rice-wheat system. Among the three ratios used, applying the required N (120 kg N ha-1) at the rate of 50% each from urea and OS (50:50) improved growth, biological (19415 and 8298 kg ha-1) and grain yields (9417 and 3451 kg ha-1 ) of rice and wheat, respectively, and also had the highest profitability (328,000 PKR) under rice-wheat cropping system. In both years, the yield and yield componetns, and profiatibility was higher while using mixtures of urea + AM than Urea + CR. The combine application of U + PM had the most positive, while, U + WR showed the most neagtive impact on yield and profitability under rice-wheat system. Increase in yield and yield components of the subsequent wheat crop was noticed with the increase in residual soil N (sole OS > OS + urea > sole urea > control). It can be concluded from the present findings that combined application of organic sources with urea not only improved growth, yield and yield components and profitability of the current rice crop; but their residual effects also increased yield, yield components and profitability of the subsequent wheat crop. It was therefore, suggested that application of organic sources in combination with urea (50:50) could increase the productivity, soil fertility and profitability under rice-wheat cropping system on sustainable basis.