India's Unified Payments Interface (UPI) generates rich behavioral data for over 400 million active users, yet this transactional signal remains inaccessible to most lenders for credit assessment due to data privacy restrictions. Thin-file borrowers — individuals with limited formal credit history — represent the primary beneficiaries of UPI-based credit assessment and simultaneously the population for whom bureau-based models perform least reliably. This study proposes, empirically validates, and evaluates six UPI behavioral proxy features (F4) constructed from standard loan application variables, providing a publicly replicable framework for approximating UPI transaction signals in credit scoring. Scientific validation via Spearman correlation confirms that payment_discipline_score and upi_success_ratio_proxy exhibit the expected directional relationships with default in both independent datasets (p<0.001). Using DS1: LendingClub 2016-2018 (N=300,001) and DS2: Home Credit (N=307,511) with five machine learning models, results show F4 features consistently improve default detection Recall for thin-file borrowers across all models and both datasets. CatBoost achieves +9.95% Recall gain (DS1) and Logistic Regression +6.80% (DS2). SHAP attribution confirms F4 proxies account for 19.0%–32.2% of total predictive power for thin-file borrowers, with payment_discipline_score ranking as the single most predictive feature in Home Credit above all bureau variables. These findings establish UPI behavioral proxies as a meaningful, scientifically validated, and previously underquantified dimension of creditworthiness.
Deep Shikha, Himanshu Vasnani· Global Journal of Engineerin...· 0 citations
Oilseed crops underpin edible-oil supply, livestock feeding, industrial feedstocks and rural incomes, yet recent production growth has depended heavily on harvested-area expansion and remains concentrated in a small number of crops and regions. This critical narrative review examines the status of major annual oilseeds, the biological and institutional causes of uneven genetic progress, and the extent to which conventional breeding, genomics, phenomics, genomic prediction and genome editing can improve yield, stability, product quality and sustainability. Literature published principally from 2000 to 20 May 2026 was identified through accessible scholarly indexes, DOI registries and authoritative institutional sources, with foundational earlier studies retained where necessary. The evidence indicates that breeding has delivered clear gains in adaptation, hybrid performance, oil composition and resistance to selected diseases, but progress is markedly less consistent for complex traits expressed across variable environments. Narrow breeding pools, polyploidy, structural variation, antagonism among seed yield, oil concentration and meal quality, weak phenotyping, and poorly connected seed systems constrain the conversion of gene discovery into cultivar-level impact. Pangenomes and high-density markers have improved variant discovery, while genomic selection can shorten cycles and raise selection intensity when training populations represent the target breeding population. Prediction often deteriorates across unrelated germplasm, environments and market classes, limiting claims of universal efficiency. Genome editing provides persuasive proof of concept for fatty-acid modification, flowering adaptation and shatter resistance, but transformation dependence, homoeologue redundancy, regulatory divergence and sparse multi-environment evidence impede routine deployment. The strongest path forward is therefore not technology substitution but integration: broad and strategically managed diversity, product-profile-led breeding, robust multi-environment phenotyping, dynamic genomic prediction, targeted editing, and delivery systems designed around farmers, processors and consumers. Future genetic improvement should be judged by realised, durable genetic gain per unit time and cost, together with nutritional, environmental and distributive outcomes.
P. Kumari, Deep Shikha, A. Jha et al.· Journal of Advances in Biolo...· 0 citations