Branch Network Research Articles

Climate risk and the systemic risk of banks: A global perspective

This paper explores the impact of climate risk on the systemic risk of banks around the world and examines its influence channels. Our findings indicate that a country’s exposure to climate risk can significantly increase the systemic risk level of its banks. Moreover, we find that the increased bank systemic risk due to higher climate risk is mostly driven by worsened credit quality rather than the depreciation of the bank’s investment portfolio. The adverse impact of climate risk is mitigated when banks have higher profitability or capital adequacy. Cross-sectionally, this effect is particularly significant for banks with extensive branch networks, high importance in the domestic credit market, a lack of dividend payments, and those classified as commercial banks. We also find that banks located in countries with higher loan interest rates, worse regulatory quality, and higher carbon emission intensity are more impacted by climate risk.

Edge and dense attention U-net for atrial scar segmentation in LGE-MRI

The segmentation of atrial scars in LGE-MRI images has huge potential value for clinical diagnosis and subsequent treatment. In clinical practice, atrial scars are usually manually calibrated by experienced experts, which is time-consuming and prone to errors. However, automatic segmentation also faces difficulties due to myocardial scars’ small size and variable shape. The present study introduces a dual branch network, incorporating edge attention, and deep supervision strategy. Edge attention is introduced to fully utilize the spatial relationship between the scar and the atrium. Besides, dense attention is embedded in bottom layer to solve feature disappearance. At the same time, deep supervision accelerates the convergence of the model and improves segmentation accuracy. The experiments were conducted on the 2022 atrial and scar segmentation challenge dataset. The results demonstrate that the proposed method has achieved superior performance.

Face forgery video detection based on expression key sequences

In order to minimize additional computational costs in detecting forged videos, and enhance detection accuracy, this paper employs dynamic facial expression sequences as key sequences, replacing original video sequences as inputs for the detection model. A spatio-temporal dual-branch detection network is designed based on the visual Transformer architecture. Specifically, this process involves three steps. Firstly, dynamic facial expression sequences are localized as key sequences using optical flow difference algorithms. Subsequently, the spatial branch network employs the focal self-attention mechanism to focus on dynamic features of expression-relevant regions and uses Factorization Machines to facilitate feature interaction among multiple key sequences. Meanwhile, the temporal branch network concentrates on learning the temporal inconsistency of optical flow differences between adjacent frames. Finally, a binary classification linear SVM combines the Softmax values from the two branch networks to provide the ultimate detection outcome. Experimental results on the Faceforensics++ dataset demonstrate: (a) replacing whole video sequences with facial expression key sequences effectively reduces training and detection time by nearly 80% and 90%, respectively; (b) compared to state-of-the-art methods involving random sequence/frame extraction and key frame extraction based on video compression techniques, the proposed approach in this paper presents a more competitive detection accuracy.

Development of a multi-level feature fusion model for basketball player trajectory tracking

To solve the problems of low matching degree, long tracking time, and low accuracy of multi-target tracking in the process of athlete motion trajectory tracking using deep learning technology, a new athlete motion trajectory tracking model was proposed in this study. The study first optimized the current object detection algorithm in basketball, utilized a hybrid attention mechanism to extract object features, and improved the non-maximum suppression strategy. Then, a hybrid branch network was introduced to improve the residual network and a new athlete identity recognition model was proposed. Finally, a new trajectory tracking model was designed by combining the object detection model and the athlete identity recognition model. The research results indicated that in the object detection experiment, the detection time of the proposed object detection algorithm was always below 0.4 s, and its average accuracy reached up to 0.63. In trajectory tracking testing, the final built tracking model had a multi-target tracking accuracy of up to 0.98, and its tracking overlap rate was as low as 0.02. This study has the following two contributions. Firstly, a new model of athlete trajectory tracking is proposed, which improves the accuracy and efficiency of multi-target tracking by optimizing object detection algorithm and introducing hybrid branch network. Second, the model has excellent performance in both object detection and track tracking, which can not only provide a new solution for athletes' motion trajectory tracking, but also significantly improve the effect of motion tracking.

Impact of Non-Performing Assets on Financial Health of Banks

The banking sector is a crucial financial service industry that supports development plans by channelling funds for productive purposes, facilitating the flow of funds from surplus to deficit units, and aiding in the implementation of government financial and economic policies. Banks fulfil social objectives through priority sector lending, extensive branch networks, and employment generation. Maintaining asset quality and profitability is essential for the survival and growth of banks. However, a significant challenge faced by the banking sector is the prevalence of Non-Performing Assets (NPAs). The Reserve Bank of India defines an NPA as “an asset, including a leased asset, that ceases to generate income for the bank.” Major causes of NPAs include wilful default, misuse of borrowed funds, and inadequate pre-loan inquiries. As of June 30, 2018, the Gross NPA of Indian banks was ₹10.03 lakh crores, with Public Sector Banks accounting for 88.74% of this total. The top five Public Sector Banks—SBI, PNB, IDBI, BOI, and BOB—make up 46.67% of the Gross NPAs. Private Sector Banks hold 11.26% of the total Gross NPAs, with leading banks being ICICI, AXIS, and HDFC. The primary aim of this paper is to examine the causes and effects of NPAs in the banking sector.

A Prior-Guided Dual Branch Multi-Feature Fusion Network for Building Segmentation in Remote Sensing Images

The domain of remote sensing image processing has witnessed remarkable advancements in recent years, with deep convolutional neural networks (CNNs) establishing themselves as a prominent approach for building segmentation. Despite the progress, traditional CNNs, which rely on convolution and pooling for feature extraction during the encoding phase, often fail to precisely delineate global pixel interactions, potentially leading to the loss of vital semantic details. Moreover, conventional CNN-based segmentation models frequently neglect the nuanced semantic differences between shallow and deep features during the decoding phase, which can result in subpar feature integration through rudimentary addition or concatenation techniques. Additionally, the unique boundary characteristics of buildings in remote sensing images, which offer a rich vein of prior information, have not been fully harnessed by traditional CNNs. This paper introduces an innovative approach to building segmentation in remote sensing images through a prior-guided dual branch multi-feature fusion network (PDBMFN). The network is composed of a prior-guided branch network (PBN) in the encoding process, a parallel dilated convolution module (PDCM) designed to incorporate prior information, and a multi-feature aggregation module (MAM) in the decoding process. The PBN leverages prior region and edge information derived from superpixels and edge maps to enhance edge detection accuracy during the encoding phase. The PDCM integrates features from both branches and applies dilated convolution across various scales to expand the receptive field and capture a more comprehensive semantic context. During the decoding phase, the MAM utilizes deep semantic information to direct the fusion of features, thereby optimizing segmentation efficacy. Through a sequence of aggregations, the MAM gradually merges deep and shallow semantic information, culminating in a more enriched and holistic feature representation. Extensive experiments are conducted across diverse datasets, such as WHU, Inria Aerial, and Massachusetts, revealing that PDBMFN outperforms other sophisticated methods in terms of segmentation accuracy. In the key segmentation metrics, including mIoU, precision, recall, and F1 score, PDBMFN shows a marked superiority over contemporary techniques. The ablation studies further substantiate the performance improvements conferred by the PBN’s prior information guidance and the efficacy of the PDCM and MAM modules.

Инструменты разработки стратегии развития образовательной экосистемы аспирантуры вуза

Determining the prospects for the development of socio-economic systems is associated with the procedures for developing a strategy, usually based on the results of an analysis of external and internal environmental factors and the subsequent determination of goals, from which the core of the strategy is formed. However, the distribution of methods for implementing strategy development algorithms and their combination largely depends on the object of development. The university's postgraduate studies are specific both in terms of regulatory support and the structure of the postgraduate course itself. Of particular interest is the university’s graduate school, the structure of which is distributed across a branch network, which opens up the possibility of considering the prospects for the development of graduate school from the point of view of the ecosystem approach. The work shows that with the help of well-known methods and procedures for conducting analysis and synthesis within the framework of the proposed algorithm, it is possible to build strategic prospects for the development of a network of postgraduate schools of university branches, aimed at increasing the effectiveness of the defense of postgraduate graduates, while solving the problems of the development of territories, government and business in based on synergistic effects characteristic of ecosystems.

A Faster and Lightweight Lane Detection Method in Complex Scenarios

Lane detection is a crucial visual perception task in the field of autonomous driving, serving as one of the core modules in advanced driver assistance systems (ADASs).To address the insufficient real-time performance of current segmentation-based models and the conflict between the demand for high inference speed and the excessive parameters in resource-constrained edge devices (such as onboard hardware, mobile terminals, etc.) in complex real-world scenarios, this paper proposes an efficient and lightweight auxiliary branch network (CBGA-Auxiliary) to tackle these issues. Firstly, to enhance the model’s capability to extract feature information in complex scenarios, a row anchor-based feature extraction method based on global features was adopted. Secondly, employing ResNet as the backbone network and CBGA (Conv-Bn-GELU-SE Attention) as the fundamental module, we formed the auxiliary segmentation network, significantly enhancing the segmentation training speed of the model. Additionally, we replaced the standard convolutions in the branch network with lightweight GhostConv convolutions. This reduced the parameters and computational complexity while maintaining accuracy. Finally, an additional enhanced structural loss function was introduced to compensate for the structural defect loss issue inherent in the row anchor-based method, further improving the detection accuracy. The model underwent extensive experimentation on the Tusimple dataset and the CULane dataset, which encompass various road scenarios. The experimental results indicate that the model achieved the highest F1 scores of 96.1% and 71.0% on the Tusimple and CULane datasets, respectively. At a resolution of 288 × 800, the ResNet18 and ResNet34 models achieved maximum inference speeds of 410FPS and 280FPS, respectively. Compared to existing SOTA models, it demonstrates a significant advantage in terms of inference speed. The model achieved a good balance between accuracy and inference speed, making it suitable for deployment on edge devices and validates the effectiveness of the model.

Evaluation of Telemedicine Experience: Artificial Intelligence in Cancer Care

Background. To date, one of the key tasks of our time, which has yet to be solved, is to provide medical services remotely using constantly advancing information and communication technologies. It is medical sciences that urgently needs ICT tools for various scopes: providing medical care in remote regions, organizing continuous education of medical personnel, managing electronic patient records, implementing mobile diagnostic devices, and managing network of branches or medical facilities at the institutional level. Telemedicine is a necessity, especially for patients with comorbid chronic diseases like cancer. Objective. To evaluate utilization of digital technologies at various stages of cancer care, through the example of artificial intelligence. Materials and methods. A systematic literature review was conducted using PRISMA. The search was carried out in such databases as Elibrary, PubMed, MEDLINE, Google Scholar by keywords “Telemedicine in oncology”, “COVID-19 in oncology”, “Artificial Intelligence”, “Digital Technologies”, “Data Personalization”, and “Teleoncology”. Publications not primarily focused on evaluating telemedicine technologies in oncology were excluded from the review process. Results. The literature review was conducted to consider the rapid integration of telemedicine since the pandemic, the risks associated with the widespread use of telemedicine in oncology, and the use of artificial intelligence in oncology, including the early detection and diagnosis of cancer. In conclusion, it is noted that the digitalization of healthcare radically changes the clinical workflow by expanding the possibilities for obtaining information from both medical staff and patients. Experience-based medicine is being replaced by an evidence-based, patient-centered approach. The rapidly developing artificial intelligence technologies will continue to have a great impact on the oncology in the near future. Both medical staff and scientific community must be prepared for the coming changes.

Geom-DeepONet: A point-cloud-based deep operator network for field predictions on 3D parameterized geometries

Modern digital engineering design process commonly involves expensive repeated simulations on varying three-dimensional (3D) geometries. The efficient prediction capability of neural networks (NNs) makes them a suitable surrogate to provide design insights. Nevertheless, few available NNs can handle solution prediction on varying 3D shapes. We present a novel deep operator network (DeepONet) variant called Geom-DeepONet, which encodes parameterized 3D geometries and predicts full-field solutions on an arbitrary number of nodes. To the best of the authors’ knowledge, this is the first attempt in the literature and is our primary novelty. In addition to expressing shapes using mesh coordinates, the signed distance function for each node is evaluated and used to augment the inputs to the trunk network of the Geom-DeepONet, thereby capturing both explicit and implicit representations of the 3D shapes. The powerful geometric encoding capability of a sinusoidal representation network (SIREN) is also exploited by replacing the classical feedforward neural networks in the trunk with SIREN. Additional data fusion between the branch and trunk networks is introduced by an element-wise product. A numerical benchmark was conducted to compare Geom-DeepONet to PointNet and vanilla DeepONet, where results show that our architecture trains fast with a small memory footprint and yields the most accurate results among the three. Results show a much lower generalization error of our architecture on unseen dissimilar designs than vanilla DeepONet. Training the model on 2500 cuboid designs is done within 2 h on a single A100 GPU while generating the training dataset through finite element simulations took about 27 h. Once trained, the model can predict vector fields and a single prediction can be over 105 times faster than its corresponding implicit finite element simulation if the mesh is large. The ability of the proposed model to perform efficient and accurate field predictions on variable 3D geometries, especially those discretized by different nodes and elements, makes it a valuable tool for preliminary performance evaluation and design optimizations and is the most significant contribution of the current work.

Advancing hyperspectral image classification with dual branch networks and informative feature extraction

ABSTRACT Hyperspectral imaging is increasingly important in academia and various professions, facing challenges like redundant features, inter-class correlations, and the curse of dimensionality. Principal Component Analysis and its variants, such as Sparse-PCA and Segmented-PCA, reduce the dimensionality of hyperspectral data but interpreting PCA results is complex. Our SPCA-mRMR technique integrates Sparse-PCA with a greedy feature selection method, mRMR. This, combined with a Dual Branch CNN model, improves hyperspectral image analysis, especially with noisy or limited data. Optimization reduces computational costs and enhances classification accuracy. Evaluations show our method’s efficiency, using fewer variables without compromising accuracy, crucial for advancing HSI applications.

Predictions of transient vector solution fields with sequential deep operator network

The deep operator network (DeepONet) structure has shown great potential in approximating complex solution operators with low generalization errors. Recently, a sequential DeepONet (S-DeepONet) was proposed to use sequential learning models in the branch of DeepONet to predict final solutions given time-dependent inputs. In the current work, the S-DeepONet architecture is extended by modifying the information combination mechanism between the branch and trunk networks to simultaneously predict vector solutions with multiple components at multiple time steps of the evolution history, which is the first in the literature using DeepONets. Two example problems, one on transient fluid flow and the other on path-dependent plastic loading, were shown to demonstrate the capabilities of the model to handle different physics problems. The use of a trained S-DeepONet model in inverse parameter identification via the genetic algorithm is shown to demonstrate the application of the model. In almost all cases, the trained model achieved an R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2$$\\end{document} value of above 0.99 and a relative L2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$L_2$$\\end{document} error of less than 10% with only 3200 training data points, indicating superior accuracy. The vector S-DeepONet model, having only 0.4% more parameters than a scalar model, can predict two output components simultaneously at an accuracy similar to the two independently trained scalar models with a 20.8% faster training time. The S-DeepONet inference is at least three orders of magnitude faster than direct numerical simulations, and inverse parameter identifications using the trained model are highly efficient and accurate.

Knockin' on the bank's door: The impact of U.S. bank branch closures on self‐employment dynamics

AbstractThe U.S. bank branch network has contracted since the 2010s, limiting borrowers' access to credit institutions. This paper analyzes the changes in banks' branch concentration and their effect on borrowers' choices of being self‐employed. To evaluate the impact of the bank branch closings, I use a shift‐share research design to assess self‐employment exits using zip code variation in preexisting bank market shares. I disaggregate the self‐employed into two categories: entrepreneurs whose businesses depend on business loans (incorporated self‐employed) and other self‐employed individuals (unincorporated self‐employed). Using a Community Advantage Panel Survey, I find that the proximity of credit market institutions has heterogeneous effects on self‐employment exits. While bank branch closures lead to a decline in incorporated businesses, particularly within a five‐mile radius, unincorporated businesses appear insignificantly affected.

Multimodal Sensing for Depression Risk Detection: Integrating Audio, Video, and Text Data.

Depression is a major psychological disorder with a growing impact worldwide. Traditional methods for detecting the risk of depression, predominantly reliant on psychiatric evaluations and self-assessment questionnaires, are often criticized for their inefficiency and lack of objectivity. Advancements in deep learning have paved the way for innovations in depression risk detection methods that fuse multimodal data. This paper introduces a novel framework, the Audio, Video, and Text Fusion-Three Branch Network (AVTF-TBN), designed to amalgamate auditory, visual, and textual cues for a comprehensive analysis of depression risk. Our approach encompasses three dedicated branches-Audio Branch, Video Branch, and Text Branch-each responsible for extracting salient features from the corresponding modality. These features are subsequently fused through a multimodal fusion (MMF) module, yielding a robust feature vector that feeds into a predictive modeling layer. To further our research, we devised an emotion elicitation paradigm based on two distinct tasks-reading and interviewing-implemented to gather a rich, sensor-based depression risk detection dataset. The sensory equipment, such as cameras, captures subtle facial expressions and vocal characteristics essential for our analysis. The research thoroughly investigates the data generated by varying emotional stimuli and evaluates the contribution of different tasks to emotion evocation. During the experiment, the AVTF-TBN model has the best performance when the data from the two tasks are simultaneously used for detection, where the F1 Score is 0.78, Precision is 0.76, and Recall is 0.81. Our experimental results confirm the validity of the paradigm and demonstrate the efficacy of the AVTF-TBN model in detecting depression risk, showcasing the crucial role of sensor-based data in mental health detection.

FDB-Net: Fusion double branch network combining CNN and transformer for medical image segmentation.

The rapid development of deep learning techniques has greatly improved the performance of medical image segmentation, and medical image segmentation networks based on convolutional neural networks and Transformer have been widely used in this field. However, due to the limitation of the restricted receptive field of convolutional operation and the lack of local fine information extraction ability of the self-attention mechanism in Transformer, the current neural networks with pure convolutional or Transformer structure as the backbone still perform poorly in medical image segmentation. In this paper, we propose FDB-Net (Fusion Double Branch Network, FDB-Net), a double branch medical image segmentation network combining CNN and Transformer, by using a CNN containing gnConv blocks and a Transformer containing Varied-Size Window Attention (VWA) blocks as the feature extraction backbone network, the dual-path encoder ensures that the network has a global receptive field as well as access to the target local detail features. We also propose a new feature fusion module (Deep Feature Fusion, DFF), which helps the image to simultaneously fuse features from two different structural encoders during the encoding process, ensuring the effective fusion of global and local information of the image. Our model achieves advanced results in all three typical tasks of medical image segmentation, which fully validates the effectiveness of FDB-Net.

МОДЕЛІ БІЗНЕСУ УКРАЇНСЬКИХ ОЩАДНИХ БАНКІВ

In the banking system, savings banks represent a special component, as they form their resource base mainly due to the accumulation of population savings. Problem Statement. Ukrainian savings banks are a factor in ensuring financial stability, but at the same time they are vulnerable to depositors’ panic in conditions of systemic stresses. Therefore, the analysis of their activities is important for understanding the prospects of the banking system. Savings banks in Ukraine differ significantly in scale and level of business technology. Leading savings banks are planned by the state for privatization, so they are designed to improve their investment attractiveness, at the same time, the status of state ownership gives such banks additional advantages in the market. The purpose is a comparative analysis of the business models of savings banks in Ukraine and the behavior of such banks on the market. Methods. The authors used the methods of comparative analysis, logical generalization, analysis and synthesis. Results. In Ukraine, savings banks are divided by origin into two categories ( state and private capital), and by a business model into those, focused on lending to business clients and those with a balanced composition of the loan portfolio. The monopoly of the state bank was broken by the entry of banks with private capital to the market. Savings banks are identified based on the ratio of funds raised by individuals to the total amount of balances on customer accounts. A blueprint of two business models for the savings bank segment was built, the structure of assets and liabilities, the development of the branch network and market positions in terms of deposits were compared. The analysis of the efficiency of a sample of savings banks was carried out and compared with the indicators of the banking system (profitability, return on operating expenses, profitability of the loan portfolio, cost of funds of individuals, the branching of branch network), as well as the impact of the business model on the investment attractiveness of banks was assessed, the volumes of savings and allocation of funds in loans to individuals were compared. Conclusions. The research made it possible to identify a specific group of banks with heterogeneous business models: firstly, banks that use public funds mainly to finance business clients, secondly, banks that have a relatively balanced credit portfolio for individuals and legal entities. The segment of Ukrainian savings banks is clearly dominated by two large state-owned banks, and given the state of war and citizens' trust in the state itself, there is no reason to expect a change in leaders. Digitization of products and processes will allow savings banks to compensate for the reduction of the branch network, but other banks also take advantage of this opportunity. and return on investment in technological innovation projects will bring effect in the medium term. To a large extent, the amount of savings accumulated by banks depends on two factors - customer trust and assessment of service quality. Savings bank managers should pay primary attention to this. Excessively high dependence of banks on the funds of individuals can be considered as a disadvantage, rather than as an advantage, if a bank itself works inefficiently.

Data envelopment analysis for identification of bank branches appropriate locations in terms of their efficient operation

One of the main banking activities is the branch network. It provides the effective banking, the profitability. Choosing the right location of branches is very important for the bank effective operation. Random or intuitively locations can have a negative impact on key performance indicators in the future. The correct and thoughtful choice of the bank branch location ultimately determines its maximum efficiency. The paper concerns with the determining of the bank branch location in terms of thorough mathematical calculation and many factors influencing bank activity. We developed a special calculation method using the DEA (Data Envelope Analysis) methodology, considering financial, branch location, location features, etc. The paper dwells on the issue of one large branch effectiveness comparing to several smaller branches covering a wider consumer area on the example of the branch on A. Sharifzade street, Baku, Azerbaijan. Indeed, it is important to consider the location in terms of its geolocation and landscape. However, one of the main issues is expediency of establishing one large or several small branches in densely populated areas. Moreover, it is necessary to take into account the infrastructure to improve the bank performance. To consider this issue, we use both hypothetical and statistical data of Capital Bank. It is one of the largest banks in Azerbaijan. Also it has a large network of branches. The article examines expediency of establishing one large or several small branches in the area close to the existing branch of Capital Bank on A. Sharifzade street. The efficiency of the current operating branch was compared with the total efficiency of virtual branches in several combinations. We analysed the indicators of the Inshaatchylar branch and virtual branches in different combinations in different locations in accordance with DEA CRS (Constant Return to Scale) method. Additionally, we determined the effectiveness of both the Inshaatchylar branch and virtual branches in various combinations. Thus, the highest score is the most effective one.

Dual-branch transfer learning in Raman spectroscopy for bacterial quantitative analysis

Accurate quantification of bacteria is critical for ensuring food safety, advancing biomedical research, and a range of other pressing concerns. Raman spectroscopy is a popular technique for quantitative analysis due to its benefits of being fast, non-destructive, and highly sensitive. However, the accuracy of the transfer model is often limited by factors such as differences in equipment and environmental noise, which limits the popularization of Raman spectroscopy. In this paper, we propose an approach that overcomes this challenge by introducing a dual branch network based on Continuous Wavelet Transform (CWT) for model transfer. Our model comprises dual branches that perform distinct tasks. The spectral learning branch is responsible for extracting features from the spectral domain. The time-frequency map learning branch employs CNNs for extracting the multi-scale information-rich features. The proposed method is used for the quantitative analysis of Escherichia coli. The proposed approach significantly outperforms traditional methods in improving prediction accuracy. It offers a much-needed solution to the long-standing challenge of Raman spectroscopy in the field of bacterial quantitative analysis. With our approach, we can expect to see Raman spectroscopy more widely adopted in the future.

Where the money is: branch network structure and bank profitability in Switzerland

This paper investigates the impact of the geographic concentration of branch networks on bank profitability in Switzerland. Leveraging Switzerland's distinctive federalist fiscal structure, where communes set their own income tax rates, we also explore whether the tax burden of branch locations moderates this relationship. Using a hand-collected dataset of branch networks of commercial banks, we find that geographic branch network concentration positively affects bank profitability but only when banks concentrate their branches in low-tax communes. This suggests that the proximity to wealthy clients, who are more likely to reside in low-tax areas, enhances bank profitability.

An Analysis of Indian Overseas Bank's Case Study on the Conceptual Framework of Lending Technologies for Financing Small and Medium-sized Businesses

This to examine the Indian Overseas Bank’s credit facilities MSMEs with various financing options available and also examine the constraints in credit facilities. The sample respondents was 90, which comprised of seventy-one manufacturing enterprises and nineteen service enterprise respondents. Statistical tools such as Percentage analysis, Chi-square Test, factor analysis was used to analyse the data. The study revealed that, among manufacturing enterprise and service enterprise respondents, majority (67.60 per cent and 57.89 per cent) were small entrepreneurs. in middle age group (37.78 per cent). About 40 per cent were graduates and 78.89 per cent were sole proprietors. There was a significant association between type of business and age group, form of organization and business experience. 98 per cent of respondents were aware about term loan of which 65.90 per cent availed loan. 91 per cent of the respondents were aware of working capital finance of which 70.73 per cent availed loan. Bank officers (67.77 per cent) were main source of information. The source of finance (64.44 per cent) was IOB loan. They were willing to avail loan amount of Rs. 1-10 lakhs for two years. Maximum respondents repaid 25-50 per cent of loan. Difficulties faced by the customers in availing credit facilities were grouped under seven factors. Top five ranks were given to the statements such as; network of bank branches is not good, no wide range of services, non-availability of timely rehabilitation finance, lack of dissemination of information and lack of MSME loan processing centres at key locations. Majority of the respondents suggested for specialized branches of MSMEs (40 per cent).