Accurate prediction of agricultural yield is extremely important to
ensure food security and to cope with the challenges created by climate change and natural disasters. Forecasting agricultural yield is
a challenging task due to the complex nature of variables (fertiliser,
rainfall, temperature and others) that affect agricultural production.
This study employs six supervised machine learning algorithms:
Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN) to build a
predictive model using 49 years of historical data (1973-2021) on
paddy, wheat, and maize. Model performance was evaluated using
Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean
Absolute Percentage Error (MAPE), and Root Mean Squared Error (rMSE). Results show that DT and RF models are the most
precise with MSE 1% to 5%, MAE of 8% to 21%, followed by
SVM and CNN. Key predictors of crop yield include area cultivated,
capital expenditure, banking expansion, rainfall, temperature, and
fertilizers, while irrigation and road network were less significant.
The study recommends that farmers prioritize commercial farming, agricultural equipment, and timely available of fertilizer application. The Government of Nepal (GoN) should redirect subsidies
towards agricultural mechanization, ensure timely supply fertilizer,
and expand banking services in agricultural areas.

This study examines how transforming from non-profit oriented to profit-oriented MFIs in Nepal impacted their performance. A mixed-methods Approach was applied where quantitative data was analysed using a Propensity Score Matching (PSM), followed by qualitative thematic analysis. The results show that the transformation of MFIs reduces their profitability and operational self-sufficiency in the short run but increases in the long run. Further, the study found that the number of clients and the loan size of profit-oriented MFIs are increasing in Nepal, which suggests that the MFIs in Nepal are drifting away from their main mission of social welfare, also known as mission drift.

This paper intends to understand the impact of bank competition on credit risk and further determine if the association between competition and credit risk depends on bank stability, specifically focusing on commercial banks of Nepal. The study spans from Fiscal Year 2011 to 2022 and incorporates various control variables, including macroeconomic, bank-specific, Covid-19 pandemic and regulatory factors. We incorporate a dynamic panel data model and find that while increased competition leads to an increase in credit risks, this effect is reversed in a stable banking environment with strong capitalization, profitability, and steady earnings. Our findings assist policymakers in achieving a more optimal equilibrium between promoting competition and safeguarding financial stability, while also limiting excessive risk-taking. Additionally, it can provide guidance to bank management in improving their risk management practices.