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.

Vertical Enhancement of Fodder Production of Maize Zea Mays L. Through Nitrogen Management and Cultural Techniques

Optimum nitrogen, its placement methods and seeding rates are important for enhancement of qualitative maize fodder production. This study therefore was conducted to determine how nitrogen, seed rates, N placement methods, N application timings, seed sowing patterns and their interactive effect can alter fodder yield. Field experiments thus were conducted at Students Farm, Department of Agronomy, Sindh Agriculture University, Tandojam, Pakistan, located at (25o25’60’N 68o31’ 60E) during 2007-2008 and 2008-2009. In all the experiments, maize variety Akbar was sown for fodder production. The study on effect of nitrogen levels and placements on maize fodder production consisted two seasons (spring and autumn), three N placement methods (broadcast, fertigation and side dressing) and five N levels (00, 60, 100, 140 and 180 kg ha-1). Application of 140 kg N ha-1 through fertigation resulted maximum leaves plant-1, stem girth, leaf area, leaf area index, leaf area duration, N concentration, N uptake, crude protein, crude fibre, crude ash and green fodder yield. Further increase in N levels exhibited non-significant increase in the values of plant traits except plant height; crop growth rate and total dry matter were maximum at 180 kg N ha-1. N broadcast or side dressing even at higher N rates (180 kg ha-1) did not show higher values of all plant traits as compared to N- fertigation. An antagonist interactive effect of N rates and placement methods was noted on net assimilation rate, being maximum in control plots and decreased as the N rates increased regardless of N placement methods. Maize phenology changed with increasing N fertilizer rates and placement methods. To reach V10 stage, application of 140 or 180 kg N ha-1 attained maximum days under N fertigation method. Maize also took more days to reach tasselling and harvesting stages respectively at higher N application at 180 kg N ha-1 through broadcast followed by application of 140 kg N ha-1 either by fertigation or broadcast, however, early tasselling and harvesting stages appeared in the control plots. The field investigations on effect of nitrogen scheduling and placement methods on maize fodder production, comprised growing seasons (spring and autumn), N placement methods (broadcast, fertigation and side dressing) and N scheduling (00, two spilt (at sowing and V4 stages), three spilt (at sowing, V4 and V6 stages), four spilt (at sowing, V4, V6, and V8 stages), five spilt (at sowing, V4, V6, V8, V10 and VT stages). Split application of 140 kg N ha-1 through fertigation at sowing,V4 and V6 stage recorded maximum leaves, plant height, stem girth, leaf area, leaf area index, leaf area duration, crop growth rate, total dry matter, N concentration, N uptake, crude protein, crude fibre, crude ash and green fodder yield compared to two, four or five N split applications. Further N split reduced the values of all traits. Opposite response of net assimilation rate was observed, being higher in the control plots and lower in the plots treated with nitrogen. Maize phenological traits had non-significant response from V4 to V6 growth stages. Three split N applications of 140 kg N ha-1 during sowing, V4 and V6 through fertigation significantly took more days to reach V8, V10 and tasselling stages respectively. However, at harvest maize fodder took more days in two N split applications through broadcast during sowing and V4 growth stage. Studies on effect of seed rates and row directions on maize fodder production involved seasons (spring and autumn), row directions (north to south, east to west, north-east to south-west, north-west to south-west, and cross sowing and seed rates (150, 175, 200, 225 and 250 kg ha-1). Maximum leaves, plant height, stem girth, leaf area, crop growth rate, total dry matter, N content, N uptake, crude protein and fodder yield were found when crop was sown through north-south row direction at 150- 175 kg ha-1 seed rate. Higher net assimilation rate was observed in cross sowing and seeding rate of 175 kg ha-1. Seed rates and row directions had non-significant effect on germination, crude fat, crude ash and all the phenological traits of maize. For enhancement of maize fodder production, present investigations conclude and recommend that maize could be sown at seed rate of 175 kg ha-1 by north- south rows orientation. Nitrogen would be split applied at 140 kg N ha-1 through fertigation method during sowing, V4 and V6 stages