International Journal of Professional Practice

Influence of Digital Loan Applications on Loan Performance of Microfinance Banks in Kenya

Faith Waithira Waweru, Gillian Mwaniki, Nancy Rintari — Fri, 15 May 2026 00:00:00 +0000

Microfinance banks play a critical role in promoting financial inclusion by serving underserved populations. However, the sector continues to experience high levels of non-performing loans, which stood at 32.9% as of 30 June 2023. This has prompted many microfinance banks to adopt digital innovations, such as digital loan applications, to improve loan performance. The objective of this study was to examine the influence of digital loan applications on the loan performance of microfinance banks in Kenya. The study adopted an ex post facto research design guided by the pragmatism research philosophy. The target population comprised 348 loan officers drawn from the 13 licensed microfinance banks in Kenya. Proportionate stratified sampling was used to determine the sample size. Both primary and secondary data were utilized in the study. Primary data were collected using semi-structured questionnaires, while qualitative data were analyzed using thematic analysis. Quantitative data were analyzed using descriptive and inferential statistics with the aid of SPSS version 28. Descriptive statistics included means and standard deviations, whereas inferential statistics comprised Pearson correlation and logistic regression analysis. The findings revealed that digital loan applications had a strong and statistically significant positive relationship with loan performance (r = 0.695, p < 0.05). Regression results further established that digital loan applications significantly and positively influenced loan performance among microfinance banks in Kenya (β = 3.884, p < 0.05), leading to the rejection of the null hypothesis. Qualitative findings indicated that the ease of access to digital lending increases the risk of borrower over-indebtedness, as clients often obtain multiple loans from different platforms with minimal assessment of repayment capacity, thereby increasing default rates. The study recommends that microfinance banks enhance their digital loan platforms to support seamless applications, faster approvals, timely disbursements, user-friendly interfaces, and accessible customer support services.

Determinants of Animal Manure Adoption Among Smallholder Farmers in Garbatulla Sub-County, Isiolo County, Kenya

Ahmad Abagana Ille, Rosemarry Kirambia, David Mushimiyimana — Wed, 08 Jul 2026 00:00:00 +0000

Animal manure is an important component of sustainable soil fertility management, yet its adoption among smallholder farmers remains limited in many arid and semi-arid regions of Kenya. This study investigated the determinants of animal manure adoption among smallholder farmers in Garbatulla Sub-County, Isiolo County, Kenya. A cross-sectional mixed-methods design was employed, involving 202 randomly selected farmers. Quantitative data were analyzed using descriptive statistics and binary logistic regression, while qualitative data from key informant interviews and focus group discussions were analyzed thematically. The findings revealed that farm location and pesticide use were significant determinants of animal manure adoption, whereas socio-demographic factors such as age, gender, education, household size, and farm size did not significantly influence adoption decisions. Qualitative findings further identified transportation costs, labor requirements, and limited extension support as key barriers to effective manure utilization. The study concludes that improving access to manure resources, strengthening agricultural extension services, promoting integrated crop–livestock farming, and implementing location-specific interventions are essential for increasing adoption of animal manure. These measures will enhance sustainable soil fertility management, improve agricultural productivity, and contribute to climate-smart agriculture and food security in Kenya's arid and semi-arid regions.

The Impact of Records Management Procedures on Service Delivery at Rift Valley Institute of Science and Technology, Kenya

Judy Cherono Sang, Goudian Gwademba — Thu, 09 Jul 2026 00:00:00 +0000

Technical colleges are vital for bridging global workforce skills gaps. This paper evaluates how records management practices impact service delivery within technical institutes in Nakuru County. This study investigates the impact of records management procedures on service delivery in technical colleges, addressing a critical issue of efficiency and effectiveness in educational services. Outdated equipment, poor facilities, and inefficient records management cause declining student satisfaction and institutional performance. The objectives were to assess the effects of policy development and implementation, as well as electronic records management, on service delivery. Conducted over three months, the study utilised a descriptive research design to comprehensively document and analyse current practices and their impacts. This study targeted 1,750 respondents at the Rift Valley Institute of Science and Technology, comprising 300 administrative staff, 250 academic staff, 1,000 students, and 200 support staff. Stratified random sampling was applied to ensure representation of each category, with a 10% proportionate allocation from every stratum, resulting in a sample size of 175 respondents. Primary data was gathered using a single, standardized questionnaire featuring a 5-point Likert scale, designed around universal user-experience benchmarks to ensure applicability across all respondent categories. Instrument validity was established via content and expert judgment, while reliability was verified using Cronbach’s Alpha. Data from the main study were analyzed using SPSS Version 25.0, descriptive statistics, ANOVA, and multiple linear regression to examine the influence of records management practices on institutional service delivery. The study recommended the need for technical colleges to introduce continuous training and awareness programs to educate the students and staff on ERM and RMP to enhance service delivery in the institution. Additionally, RVIST should put adequate measures to promote equality in service delivery between both genders.

Evaluation of the Performance of the Small Ruminant Industry in Mandera County, Kenya

Amin Abdi Issak, William Bariu Ncene, Hellen Njagi — Thu, 09 Jul 2026 00:00:00 +0000

Small ruminant production is a key component of pastoral livelihoods and food security in Mandera County, Kenya. This study investigated disease occurrence, veterinary delivery, climate impacts, market integration, and value chain constraints affecting Mandera County's small ruminant industry to fill a gap in integrated evidence. Using a mixed-methods cross-sectional design, researchers combined structured surveys of 370 pastoralist households across six sub-counties, six focus group discussions, six key informant interviews with veterinary and extension officers, and a review of 2022–2024 climate records. Regression analysis, Pearson correlation, one-way ANOVA and thematic analysis were applied. Reported disease occurrence was high, with 68.1% of respondents reporting PPR in goat herds and 71.9% in sheep flocks, while 41.9% reported CCPP occurrence in goats. Veterinary service access was limited, with only 31.9% of pastoralists reporting regular access, due to geographical barriers (60.8% living beyond 15 km) and financial constraints (81.9% reporting services as unaffordable). Climate variability impacts were substantial, with 89.0% of respondents reporting changes, particularly increased drought frequency (67.0%) and unpredictable rainfall (45.0%), leading to reduced herd sizes (72.0%) and high mortality (40.0%). Market integration was constrained by dominant local market channels (65.1%), information asymmetries and limited value addition (72.0%). Regression analysis accounted for 79.4% of the variation in small ruminant industry performance (R² = 0.794, Adjusted R² = 0.780, p < 0.001), identifying drought frequency (β = -0.387, p < 0.001), reported PPR occurrence (β = -0.245, p < 0.001) and market access (β = 0.275, p < 0.001) as the strongest predictors. Disease burden, inadequate veterinary services, climate stress and market integration constraints are significantly associated with reduced industry performance in Mandera County. The study recommends establishing community-based animal health worker systems, implementing climate-resilient feeding strategies and developing pastoralist cooperatives for improved market integration.

SVM Model with Hybrid Parameter Tuning Strategy for Colon Cancer Classification in Nairobi County

Rukia Sharif, Lawrence Mwenda, Mutua Murungi, Job Mwale Magare — Thu, 09 Jul 2026 00:00:00 +0000

Colon cancer remains one of the leading causes of cancer-related deaths worldwide, with recent evidence pointing to a rising incidence in Nairobi County, Kenya. This study designs and evaluates a region-specific Support Vector Machine (SVM) classification model with a hybrid parameter-tuning algorithm for accurate colon cancer diagnosis in Kenyan hospitals. The work addresses diagnostic delays driven by a shortage of pathologists, lengthy manual slide reviews, and limited access to advanced procedures. Using the HIPAA-compliant LC25000 histopathological image dataset, we applied feature selection, normalization, and image augmentation to improve model robustness. Our two-stage hybrid hyperparameter-tuning strategy first performed a coarse Grid Search (C ∈ {0.1, 1, 10, 100}, γ ∈ {10⁻⁶, 10⁻⁵, 10⁻⁴}) followed by a Random Search (C ∈ [0.01, 100], γ ∈ [10⁻⁷, 10⁻⁵]) on the intersection of the top 10% configurations, enabling dense sampling of promising ranges. This approach leveraged SVM strengths in handling small, high-dimensional datasets, applying robust regularization, and weighting classes to address imbalance while reducing cross-validation variance by 15–20%. Compared to standalone grid and Random Search methods, the hybrid model achieved 83.0% accuracy (improvements of 1.5% and 2.0%), an F1-score of 82.4%, malignant recall of 81.0%, and benign precision of 84.0%. In practice, these gains translate to dozens more correctly classified slides per 4,000, representing an impactful improvement for resource-limited clinics in Nairobi. At Kenyatta National Hospital (KNH), the SVM model correctly identified 73 of 77 positive cases, yielding 94.81% sensitivity (recall) and minimizing missed colon cancer diagnoses. These findings demonstrate that tailored, efficient machine learning models can strengthen diagnostic capacity where expert resources are scarce. Future work includes collecting 200 balanced KNH images (100 benign, 100 malignant) for proper validation, implementing Bayesian optimization with an expected improvement acquisition function, and training on combined histopathology and clinical data.