The lunar calendar is often overlooked in time-series data modeling despite its importance in understanding seasonal patterns, as well as economics, natural phenomena, and consumer behavior. This study aimed to investigate the effectiveness of the lunar calendar in modeling and forecasting rainfall levels using various machine learning methods. The methods employed included long short-term memory (LSTM) and gated recurrent unit (GRU) models to test the accuracy of rainfall forecasts based on the lunar calendar compared to those based on the Gregorian calendar. The results indicated that machine learning models incorporating the lunar calendar generally provided greater accuracy in forecasting for periods of 3, 4, 6, and 12 months compared to models using the Gregorian calendar. The lunar calendar model demonstrated higher accuracy in its prediction, exhibiting smaller errors (MAPE and MBE values), whereas the Gregorian calendar model yielded somewhat larger errors and tended to underestimate the values. These findings contributed to the advancement of forecasting techniques, machine learning, and the adaptation to non-Gregorian calendar systems while also opening new opportunities for further research into lunar calendar applications across various domains.

Various types of banking product innovations were rolled out to keep up with the needs and more advanced developments, one of which is a credit or loan facility that can be utilized by the public. This credit facility is in great demand by the public because it is very helpful, especially in terms of additional capital. However, this credit activity can also be full of risks because most of the funds are entrusted to the public. Therefore, the provision of credit must be accompanied by strict risk management. As time goes on after credit is realized, banks are faced with credit risk problems, namely bad credit. Conducting a 5C (Character, Capacity, Capital, Economic Condition, and Collateral) analysis of customers is one way for banks to reduce the risk of bad credit. In fact, even though anticipatory steps have been taken by applying the 5C analysis, there is still a risk of default due to the death of the debtor, which causes the loan to not be fully paid off. In response to the possibility of the foregoing, financial/banking institutions adopted a policy requiring debtors to obtain term life insurance for a period of time equal to the term of the loan. For this reason, banks usually cooperate with life insurance institutions. Therefore, it must be ensured that the net single premium is paid at the beginning of the credit loan. With regard to the above, this paper will provide an overview and also discuss the concept of calculating the net single premium on credit life insurance, especially for debtors who make loan transactions to banking institutions that apply loan repayments with the sinking fund concept with a period according to the loan repayment tenor. So that when the debtor dies, he can pay the remaining unpaid loan to the lending institution or bank.

The catastrophic events like earthquakes, hurricanes or flooding are characteristics for some areas, a properly calculated annual premium would be closely as high as the loss insured. From an actuarial perspective, such events constitute the risk that are not insurable. On the other hand people living in such areas need protection. In order to securitize the catastrophe risk, futures or options based on a loss index could be considered. Chicago Board of Trade launched a new class of catastrophe insurance options based on new indices provided by Property Claim Services (PCS). The PCS-option is based on the Property Claim Service Index (PCS-Index). The index are used to determine and payout in writing index-based insurance derivatives. The objective of this paper is to price PCS Catastrophe Insurance Option based on PCS Catastrophe index. Gamma Distribution is used to estimate PCS Catastrophe index distribution.

The lunar calendar is often overlooked in time series data modelling, despite its importance in understanding seasonal patterns as well as economic, natural phenomena, and consumer behavior. This study aims to investigate the effectiveness of the lunar calendar in modelling and forecasting rainfall levels using various machine learning methods. The methods employed included Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to test the accuracy of rainfall forecasts based on the lunar calendar compared to those based on the Gregorian calendar. The results indicated that machine learning models incorporating the lunar calendar generally pro-vided greater accuracy in forecasting for periods of 3, 4, 6, and 12 months compared to models using the Gregorian calendar. These findings contributed to the advancement of forecasting techniques, machine learning, and the adaptation to non-Gregorian calendar systems, while also opening new opportunities for further research into lunar calendar applications across various domains.