- Trang Chủ
- Xã hội học
- Modelling the prediction of farmers' loan repayment in primary agricutural co-operative credit societies
Xem mẫu
- INTERNATIONAL JOURNAL OF MANAGEMENT (IJM)
ISSN 0976-6502 (Print)
ISSN 0976-6510 (Online)
IJM
Volume 7, Issue 2, February (2016), pp. 326-340
http://www.iaeme.com/ijm/index.asp ©IAEME
Journal Impact Factor (2016): 8.1920 (Calculated by GISI)
www.jifactor.com
MODELLING THE PREDICTION OF FARMERS' LOAN REPAYMENT IN
PRIMARY AGRICUTURAL CO-OPERATIVE CREDIT SOCIETIES
Dr.G.S.David Sam Jayakumar
Assistant professor, Jamal Institute of management,
Jamal Mohamed College, Trichy-20
J.Sathyamurti
Research scholar,
Jamal Institute of management, Jamal Mohamed College, Trichy-20
ABSTRACT
Money, the vital element of economy, is indispensable to Agriculturists too. In India the
farming community is subject to various vagaries to continue to be farmers and boost GDP of
our Nation. In this Co-operative banks also play an important role despite the low percentage
of repayment by farmers promptly coupled with high level of pressure for farmers for loan for
continuing agricultural activities while the resource is requiring its cost to make it readily
available at the time of all farming activities. There are many socio psychological factors.
Affecting recovery of lending institutions resulting in a hard situation for credit societies and
banks to continue lending. Here the study is on factors that could predict ways and means of
recovery from farmers.
Key words: Credit Societies, Repayment Factors.
Cite this Article: Dr. G.S. David Sam Jayakumar and J.Sathyamurti. Modelling The
Prediction of Farmers' Loan Repayment In Primary Agricutural Co-Operative Credit
Societies. International Journal of Management, 7(2), 2016, pp. 326-340.
http://www.iaeme.com/ijm/index.asp
1. INTRODUCTION
Institutional Credits play a vital role in economic transformation in rural development. Agricultural
credit is a crucial input required by the smallholder farmers to establish and expand their farms with the
aim of increasing agricultural production, enhancing food sufficiency, promoting household and
national income. It enables the poor farmers to take advantage of the potentially profitable investment
opportunities. The farm credit is an indispensable tool for achieving socioeconomic transformation of
the rural communities. If well applied, it would stimulate capital formation and diversified agriculture,
increase productivity, size of farm operations, and promote innovations in farming. Lending by
identifying the profile of farmers who is prompt will enable to collect the loan amount easily. This
study attempts to bring out the factors which influence the repayment capacity of co-operative farmers
of Primary Agricultural Cooperative Credit Society branches of Singalandapuram, Eragudi, and
326
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Venkatesapuram which will serve as guide to bankers to take decisions regarding sanction of farm
credit. The study focused on finding out the profile of the farmer who can make prompt payment.
Several studies have been carried out to analyze the loan repayment performance of farmers.
Ifeanyi A. Ojiako and Blessing C. Ogbukwa (2012) researched that farm credits played vital roles in
the socio-economic transformation of the rural economies. However, their acquisition and repayment
were characterized by numerous challenges major being default among beneficiaries. The implication
is that to enhance loan repayment capacity of smallholder cooperative farmers, policies and
programmes capable of increasing sizes of loan and farm holdings, or reducing household size should
be promoted. However, higher proportional increases were required for each variable to attain a desired
level of increase in loan repayment capacity. Henry De-Graft Acquah and Joyce Addo(2012)
researched that farm credit can stimulate the transfer of technology into agriculture and hence lead to
increased crop yield. The adequacy of loan amount was also studied. Empirical results from the
regression analysis found that the farm size, income and years of farming experience were positive and
significant predictors of farm loan size was also seen. Yasir Mehmood, Mukhtar Ahmad, and
Muhammad BahzadAnjum (2012) states that the productive use of agricultural credit in Pakistan is
quite limited that affects the repayments be havior of the farmers and ultimately categorization of loans
into default stages and finally auction of their lands. Data revealed that sloppy supervision by the bank
employees, miss-utilization of loans, high interest rate and change in business/residential place of the
borrowers etc. caused delay in repayments of agricultural credit. S.U.O. Onyeagocha (2012) analyzed
the loan demand requirements of rural staple and poultry farmers and the factors affecting loan size.
Results showed that the potent factors affecting loan size were farm size, level of education, enterprise
type, farmers experience and dependency ratio. The financial institutions were admonished to consider
providing start-up capital for the youths and fresh graduates. Further government was urged to provide
fiscal and monetary incentives to financial institutions supporting agriculture because of delicate nature
of farm business.
Durguner, Sena; Katchova, Ani L(2011)identified the most pertinent factors that explain farmer
repayment capacity. He found that the one year lagged working capital ratio, the debt-to-asset ratio,
and operator's age are significant variables in explaining the coverage ratio. This finding is important
because it can enhance agricultural lenders' ability to assess creditworthiness, screen borrowers,
manage loan loss reserves, and price loans, thereby decreasing lenders' costs associated with
defaulted loans and ultimately reducing the costs borne by the government and taxpayers. Amjad
Saleem, DrFarzand Ali Jan, and Rasheed Muhammad Khattak& Muhammad Imran Quraishi (2011)
researched the impact of farm and farmers’ characteristics on repayment of farm credit user for
agricultural growth and found it is significant for impact of age, education, marital status, farm type,
farm size, farm status and numbers of times credit obtained. But regression result showed significant
influence of marital status, farm type and numbers of times credit attained on repayment of farm credit.
Victor UgbemOboh and Ineye Douglas Ekpebu (2011) conducted research to determine the effects of
socio-economic and demographic factors on the rate of credit allocation to the farm sector and found
that only about 56% of the loans were invested directly in farm activities implying that the balance of
43% of the loan was diverted and spent on non-farm activities. Based on these results, the paper
recommends increased flow of capital to the bank for on-lending to farmers. In addition, loans should
be disbursed on time and banks officials should be encouraged to pay regular supervisory visits to
farmers. Finally, benefiting farmers should be given basic training on efficient management of loans in
order to curtail the high rate of loan diversion. AbebeMijena (2011) researched the factors influencing
timely credit repayment and input use (especially fertilizer) by smallholder farmers and found that
there is significant mean difference regarding Age, family size, cultivated land size, number of
livestock owned, on-farm income, amount of fertilizer used and saving habits. The result of the model
showed that family size, livestock ownership, on-farm income, non-farm income and saving habit were
the statistically significant factors influencing timely loan repayment performance positively. The study
suggests that improving the livestock sector, educating households and their family member, giving
attention in promoting non-farm activities in rural areas and promoting saving habit are some of the
important priority areas for the success of future intervention strategies for sustainable credit facilities.
J. A. Afolabi (2010) analysed loan repayment among small scale farmers and identified socio-
economic characteristics of the respondents and quantitatively determined some socio-economic
characteristics of these farmers that influence their level of loan repayments.
MalimbaMusafiriPapias; Ganesan.P (2009) state that both formal and informal financial systems
327
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
operate side by side. While the later has been playing a predominant role, cooperative societies have
emerged as an apt method of increasing the delivery of formal rural credit and savings facilities on
sustainable and non-exploitative terms albeit of financial imprudence stemming from poor
credit repayment records. Mohammad Reza Kohansal and HoomanMansoori (2009) investigated the
factors influencing on repayment behavior of farmers that received loan from agricultural bank and
found that loan interest rate is the most important factor affecting on repayment of agricultural loans.
Farming experience and total application costs are the next factors, respectively. Limsombunchai, V. C.
Gan and M. Lee (2005) analyzed thatLoan contracts performance determines the profitability and
stability of the financial institutions, and screening the loan applications is a key process in minimizing
credit risk. A good credit risk assessment assists financial institutions on loan pricing, determining the
amount of credit, credit risk management, reduction of default risk and increase in debt repayment.MC
Mashatola& MAG Darroch (2003) researched the factors affecting sugarcane farmers using a
graduated mortgage loan repayment and found that the estimated probability of a farmer in the scheme
being current on loan repayments was higher for clients with higher levels of average annual farm
gross turnover relative to loan size, and for clients with access to substantive off-farm income. Access
to off-farm income helps to provide additional liquidity to fund future operations and debt
repayments.C J Arene and G C Aneke researched (1999) and madeattempts to assess the credit system
and showed that high repayment rate farmers had a larger loan size, larger farm size, higher gross
income, shorter distance between home and source of loan, higher level of formal education, larger
household size, and higher level of adoption of innovations than low repayment rate farmers. Loan
programmes for female farmers are of great importance for the development of agriculture.
2. BANK PROFILE
PRIMARY AGRICULTURAL COOPERATIVE CREDIT SOCIETIES (PACCS)
PACCS came into being after the enactment of the Cooperative Credit Societies Act in 1904. This Act
was subsequently revised in 1912 to promote multi-purpose cooperatives and to organize non-credit
cooperatives. The first primary agricultural cooperative credit society was promoted in early 1900s and
"by early 1980s, there were about 92,000 PACCS.
To align urban banking sector with the other segments of banking sector in the context of
application or prudential norms in to and removing the irritants of dual control regime of RBI (banking
operations ) as well as State Government . Banking related functions (viz. licensing, area of operations,
interest rates etc.) were to be governed by RBI and registration, management, audit and liquidation, etc.
governed by State Governments.
The different types of Co-operative Banks are Primary Co-operative Credit Society, Central co-
operative banks, State co-operative banks, Land development banks, Urban Co-operative Banks .
3. METHODOLOGY AND DATA ANALYSIS
The present study is a census survey made to evaluate the repayment of loan amount by farmers of
three areas namely Singalandapuram, Eragudi and Venkatesapuram of Primary Agricultural
Cooperative Credit Society for the due period of April 2009 to March 2011. Data of 682 farmers were
collected from Singalandapuram branch, 243 farmers' data were collected from Eragudi branch, and
125 farmers' data were collected from Venkatesapuram branch. The purpose of study is to know the
profile of farmers those who got crop loan from Singalandapuram, Eragudi, and Venkatesapuram
branches of Primary Agricultural Cooperative Credit Society1 )to find out the personal and
demographical factors that affects the repayment of loan 2) to bring out the factors that makes impact
on farmers loan repayment 3) to give the suitable suggestions to the bankers to avoid delayed
repayment
A structured questionnaire was finalized and it comprised of five personal and demographic
factors, and13 conceptual questions . Secondary information were collected from respective branches
of Primary Agricultural Cooperative Credit Society and used. After the final data collection was over,
the collected data was analyzed with the help of statistical package namely IBM SPSS-20. The analysis
was done for three branches and a pooled analysis. The analysis has two phases, in Phase-I, descriptive
statistics was prepared and was shown for all the three branches. In Phase- II, neural network analysis
was applied to identify the variables which influence the repayment of loan. When there are factors
found more related and influential on the repayment of farmers' loan like 1. Gender 2. Age 3.
328
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Annual Income - Non-farmn income / On-farm income 4. Number of Family Members 5. Educational
Qualification 6. Land Owned 7. Crop – Paddy, Banana , Onion , Turmeric, Other Crops like cassava,
sugar cane, ground nut, Black gram. 8. Loan Amount Sanctioned 9. Loan Amount Sanctioned as Cash
10. Seed 11. Fertilizer 12. Insurance 13. Duration of Loan Period 14.Earlier Payment
Period 15. Period of Delay 16. Interest Paid 17. Location of Bank, the above 18 factors were taken into
consideration. This is to nullify the effect of factors that encourage default like 1. Waiver of loans by
government; 2. Delay in getting money from informal sources;3. Crop failure; 4. Rain defect and
unusual rainfall; 5. Price; 6. Interest;7. Duration of loan;8. Low productivity;9. Delay and inadequate
maintenance;10. Inefficient work;11. Unexpected expenses like medical bills; 12. Family
commitments;13. Investing loan amount in assets; 14. Casual attitude about interest, principal; 15.
Waiting for good crop price; 16. Amount given to friends and relatives.
4. RESULTS AND DISCUSSION
Analysis is the process of placing the data in an ordered form and extracting the meaning from them. In
other words analysis is the answer to the question, “what message is conveyed by each group of data”.
The raw data become information, only when they are analyzed and when put in a meaningful form.
Tabular representations are used for better projections. After the final data collection was over, the
collected data was analyzed with the help of statistical package namely IBM SPSS-20. The analysis
was done for three branches and a pooled analysis. The analysis has two phases, in Phase-I, descriptive
statistics was prepared and was shown for all the three branches. In Phase- II, neural network analysis
was applied to identify the variables which influence the repayment of farmers' loan.
Table 1 Location wise Descriptive Statistics of Farmers' Personal and Demographic Variables
Location of Bank
Constructs Singalandapura Venkatesapuram
Eragudi n=243 Total n=1050
m n=682 n=125
Gender Male 586(85.92%) 207(85.19%) 103(82.40%) 896(85.33%)
Female 96(14.08%) 36(14.81%) 22(17.60%) 154(14.67%)
20 – 30 1(.15%) 2(.82%) 2(1.60%) 5(.48%)
30 – 40 29(4.25%) 22(9.05%) 19(15.20%) 70(6.67%)
Age 40 – 50 224(32.84%) 56(23.05%) 34(27.20%) 314(29.90%)
50 and above 428(62.76%) 163(67.08%) 70(56.00%) 661(62.95%)
Below Rs.50,
119(17.45%) 66(27.16%) 41(32.80%) 226(21.52%)
000/-
Rs.50, 000/- -
185(27.13%) 63(25.93%) 73(58.40%) 321(30.57%)
Annual Rs.75,000/-
Income Rs.75,000/-
226(33.14%) 70(28.81%) 8(6.40%) 304(28.95%)
Rs.1,00,000/-
Rs.1,00,000/-
152(22.29%) 44(18.11%) 3(2.40%) 199(18.95%)
and above
Number of 2–4 483(70.82%) 217(89.30%) 122(97.60%) 822(78.29%)
Family 5–7 184(26.98%) 25(10.29%) 3(2.40%) 212(20.19%)
Members 7 and above 15(2.20%) 1(.41%) 0(.00%) 16(1.52%)
No formal
142(20.82%) 35(14.40%) 20(16.00%) 197(18.76%)
education
Primary
151(22.14%) 63(25.93%) 42(33.60%) 256(24.38%)
education
Educational
Secondary
Qualification 318(46.63%) 124(51.03%) 56(44.80%) 498(47.43%)
education
Degree or
technical 71(10.41%) 21(8.64%) 7(5.60%) 99(9.43%)
education
329
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table No. 2 Location wise Descriptive Statistics of Conceptual Variables
Location of Bank
Constructs Singalandapura Eragudi Venkatesapuramn=12
Total n=1050
m n=682 n=243 5
Small(below 139
422(61.88%) 53(42.40%) 614(58.48%)
2.5) (57.20%)
Nature of
Medium(2.5 -
farmer (Farm 208(30.50%) 64(26.34%) 43(34.40%) 315(30.00%)
5)
in acre)
Big(5 and 40
52(7.62%) 29(23.20%) 121(11.52%)
above) (16.46%)
Below 1 112(16.42%) 26(10.70%) 6(4.80%) 144(13.71%)
146
Land Owned 1-3 413(60.56%) 60(48.00%) 619(58.95%)
(60.08%)
(Farm in
31
acre) 3-5 105(15.40%) 31(24.80%) 167(15.90%)
(12.76%)
5 and above 52(7.62%) 40(16.46%) 28(22.40%) 120(11.43%)
208
Paddy 668(97.95%) 107(85.60%) 983(93.62%)
(85.60%)
Crop Name
Banana 0(.00%) 32(13.17%) 1(.80%) 33(3.14%)
Others 14(2.05%) 3(1.23%) 17(13.60%) 34(3.24%)
Below Rs.25, 134
396(58.06%) 53(42.40%) 583(55.52%)
000/- (55.14%)
Rs.25, 000/- - 216 80
Loan 60(48.00%) 356(33.90%)
Rs.50,000/- (31.67%) (32.92%)
Amount
Rs.50,000/- -
Sanctioned 44(6.45%) 15(6.17%) 6(4.80%) 65(6.19%)
Rs.75,000/-
Rs.75,000/- -
26(3.81%) 14(5.76%) 6(4.80%) 46(4.38%)
Rs.1,00,000/-
Below 199 60
18(14.40%) 277(26.38%)
Rs.10,000/- (29.18%) (24.69%)
Loan Rs.10,000/- - 439 165
97(77.60%) 701(66.76%)
Amount Rs.40,000/- (64.37%) (67.90%)
Received as Rs.40,000/- -
43(6.30%) 18(7.41%) 9(7.20%) 70(6.67%)
Cash Rs.70,000/-
Rs.70,000/-
1(.15%) 0(.00%) 1(.80%) 2(.19%)
and above
Below 246 76
27(21.60%) 349(33.24%)
Rs.1,000/- (36.07%) (31.28%)
Rs.1,000/- - 377 102
Loan 77(61.60%) 556(52.95%)
Rs.3,000/- (55.28%) (41.98%)
Amount
Rs.3,000/- -
Received as 48(7.04%) 12(4.94%) 13(10.40%) 73(6.95%)
Rs.5,000/-
Seed
Rs.5,000/- and
11(1.61%) 21(8.64%) 8(6.40%) 40(3.81%)
above
None 0(.00%) 32(13.17%) 0(.00%) 32(3.05%)
Below 154 43
19(15.20%) 216(20.57%)
Rs.3,000 (22.58%) (17.70%)
Loan Rs.3,000 - 300 104
44(35.20%) 448(42.67%)
Amount Rs.7,000/- (43.99%) (42.80%)
Received as Rs.7,000 - 125 55
36(28.80% 216(20.57%)
Fertilizer Rs.11,000/- (18.33%) (22.63%)
Rs.11,000 and 41
103(15.10%) 26(20.80%) 170(16.19%)
above (16.87%)
330
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Location of Bank
Constructs Singalandapura Eragudi Venkatesapuramn=12
Total n=1050
m n=682 n=243 5
Below 575 190
83(66.40%) 848(80.76%)
Rs.500/- (84.31%) (78.19%)
Rs.500/- -
67(9.82%) 22(9.05%) 9(7.20%) 98(9.33%)
crop Rs.1,000/-
Insurance Rs.1,000/- -
3(.44%) 12(4.94%) 0(.00%) 15(1.43%)
Rs.1,500/-
Rs.1,500/- and
2(.29%) 18(7.41%) 0(.00%) 20(1.90%)
above
Not applicable 35(5.13%) 1(.41%) 33(26.40%) 69(6.57%)
6 Months 0(.00%) 1(.41%) 2(1.60%) 3(.29%)
669 208
6 - 10 Months 117(93.60%) 994(94.67%)
(98.09%) (85.60%)
Duration of
10 - 12
Loan Period 10(1.47%) 30(12.35%) 5(4.00%) 45(4.29%)
Months
12 - 15
3(.44%) 4(1.65%) 1(.80%) 8(.76%)
Months
312 81
Below 30 days 35(28.00%) 428(40.76%)
(45.75%) (33.33%)
30 - 60 days 12(1.76%) 2(.82%) 1(.80%) 15(1.43%)
Earlier
60 - 90 days 8(1.17%) 2(.82%) 0(.00%) 10(.95%)
Payment
251 120
Days Not applicable 73(58.40%) 444(42.29%)
(36.80%) (49.38%)
Paid on due
99(14.52%) 38(15.64%) 16(12.80%) 153(14.57%)
date
Below 1
24(3.52%) 2(.82%) 6(4.80%) 32(3.05%)
Month
1 - 6 Months 94(13.78%) 29(11.93%) 19(15.20%) 142(13.52%)
Period of 6 - 12 Months 49(7.18%) 22(9.05%) 22(17.60%) 93(8.86%)
Delay 1 year and
85(12.46%) 66(27.16%) 25(20.00%) 176(16.76%)
above
430 124
Not applicable 53(42.40%) 607(57.81%)
(63.05%) (51.03%)
Below
41(6.01%) 11(4.53%) 5(4.00%) 57(5.43%)
Rs.1,000/-
Rs.1,000/- - 151 56
31(24.80%) 238(22.67%)
Rs.4,000/- (22.14%) (23.05%)
Rs.4,000/- -
24(3.52%) 12(4.94%) 16(12.80%) 52(4.95%)
Interest Paid Rs.7,000/-
Rs.7,000/- and
7(1.03%) 11(4.53%) 1(.80%) 19(1.81%)
above
430 124
Not applicable 53(42.40%) 607(57.81%)
(63.05%) (51.03%)
None 29(4.25%) 29(11.93%) 19(15.20%) 77(7.33%)
Status of 431 123
Prompt payer 53(42.40%) 607(57.81%)
farmer in (63.20%) (50.62%)
loan 251 120
Defaulter 72(57.60%) 443(42.19%)
repayment (36.80%) (49.38%)
331
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table 3Independent Variable Importance of PACCS Branch of Singalandapuram
Normalized
Factors Importance
Importance
Gender .136 54.4%
Age .080 32.0%
Annual Income .083 33.1%
Number of Family Members .159 63.7%
Educational Qualification .250 100.0%
Nature of farmer (Farm in acre) .117 46.6%
Land Owned (Farm in acre) .176 70.3%
Table 4 Impact of Hidden Layers on Farmers' Loan Repayment in Singalandapuram branch
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 -.295 -.035
H2 .344 -.012
H3 .362 -.029
H4 -.236 .242
H5 .097 .239
H6 -.704 -.342
H7 -.159 .543
Bias .170 .311
Percent Incorrect Predictions - Training (36.8%), Testing (33.5%)
Table 5 Estimation of Parameters for PACCS branch of Singalandapuram
Best Hidden Layer
Predictors Hidden Hidden
Rank Rank
Layer 3 Layer 7
Gender(Male) .094 7 .259 4
Age(40 - 50 ) .313 4 - -
Age(20 - 30) - - -.421 7
Annual income (Rs.1,00,000/- and above) .388 3 .397 3
Family Members(7 and above) .221 6 - -
Family Members(2 - 4) - - .097 6
Educational Qualification (Primary Education) .281 5 .467 1
Nature of Farmer (Big - 5 and above acres) .389 2 .411 2
Land Owned (3 - 5 acres) .672 1 - -
Land Owned(5 acres and above) - - .190 5
Table 6 Independent Variable Importance of PACCS Branch of Eragudi
Normalized
Factors Importance
Importance
Gender .088 37.2%
Age .205 87.0%
Annual Income .158 66.9%
Number of Family Members .159 67.3%
Educational Qualification .236 100.0%
Nature of farmer (Farm in acre) .049 20.6%
Land Owned (Farm in acre) .106 45.0%
332
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table 7 Impact of Hidden Layers on Farmers' Loan Repayment in Eragudi branch
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 .209 -.430
H2 -.276 .182
Bias .254 -.069
Percent Incorrect Predictions – Training (49.1%), Testing (43.4%)
Table 8 Estimation of Parameters for PACCS branch of Eragudi
Best Hidden Layer
Predictors Hidden Hidden
Rank Rank
Layer 1 Layer 2
Gender (Female) .028 7 .109 7
Age (40 - 50 ) .597 2 .416 3
Annual income (Rs.50,000 - 75,000/-) .562 3 .365 4
Family Members (5 - 7) .069 6 - -
Family Members (7 and above) - - .164 6
Educational Qualification (Primary Education) .727 1 - -
Educational Qualification (No formal Education) - - .464 2
Nature of Farmer (Big - 5 and above acres) .351 4 .474 1
Land Owned (3 - 5 acres) .327 5 .344 5
Table 9 Independent Variable Importance of PACCS Branch of Venkatesapuram
Normalized
Factors Importance
Importance
Gender .085 36.9%
Age .089 38.4%
Annual Income .162 70.2%
Number of Family Members .230 100.0%
Educational Qualification .147 63.6%
Nature of farmer (Farm in acre) .121 52.3%
Land Owned (Farm in acre) .167 72.5%
Table 10 Impact of Hidden Layers on Farmers' Loan Repayment in Venkatesapuram branch
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 -.429 .721
Bias .352 .877
Percent Incorrect Predictions -Training (37.6%), Testing (20.0%)
333
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table 11 Estimation of Parameters for PACCS branch of Venkatesapuram branch
Predictors Hidden Layer 1 Rank
Gender(Male) .013 7
Age(30 - 40) .255 4
Annual income (Rs.1,00,000/- and above) .536 2
Family Members(5 -7) .587 1
Educational Qualification (Primary Education) .187 5
Nature of Farmer (2 1/2 - 5 acres) .139 6
Land Owned (3 - 5 acres) .512 3
Table 12 Pooled Analysis of Independent Variable Importance of PACCS Branches
Normalized
Factors Importance
Importance
Gender .043 20.8%
Age .183 88.7%
Annual Income .169 81.9%
Number of Family Members .207 100.0%
Educational Qualification .199 96.5%
Nature of farmer (Farm in acre) .089 43.2%
Land Owned (Farm in acre) .110 53.2%
Table 13Impact of Hidden Layers on Farmers' Loan Repayment in PACCS branches
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 -.558 .854
H2 -.287 -.257
H3 .322 -.321
H4 -.922 .399
H5 -.230 .062
Bias .160 -.188
Percent Incorrect Predictions - Training (39.9%), Testing (38.5%)
Table 14 Estimation of Parameters for PACCS branches
Best Hidden Layer
Predictors Hidden Hidden
Rank Rank
Layer 3 Layer 1
Gender (Male) -.257 7 .659 3
Age (50 and above) - - .460 5
Age (20 - 30) .368 4 - -
Annual income (Rs.75,000 - Rs.$$$$1,00,000/-) - - .335 7
Annual Income (Rs.50,000 - Rs.75,000/-) .404 2 - -
Family Members (2 - 4) .298 5 .661 2
Educational Qualification (Secondary Education) - - .829 1
Educational Qualification (Degree or Technical Education) .403 3 - -
Nature of Farmer (Small - below 2.5 acres) - - .588 4
Nature of Farmer (Big - 5 and above acres) .079 6 - -
Land Owned (Below 1 acre) - - .345 6
Land Owned (5 acres and above)
.410 1 - -
334
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table 15 Impact of Hidden Layers on Farmers' Loan Repayment in Singalandapuram branch
Percent Incorrect Predictions - Training (0.2%), Testing (0.5%)
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 .451 -.246
H2 -1.141 .951
H3 -.287 .034
H4 1.180 -1.798
H5 .978 -1.505
H6 1.309 -1.520
H7 .389 -.865
H8 -.751 .488
Bias -.786 .311
Table 16 Estimation of Parameters for PACCS branch of Singalandapuram
Best Hidden Layer
Predictors Hidden Hidden
Rank Rank
Layer 1 Layer 2
Crop Name (Others) .217 9 - -
Crop Name (Paddy) - - .534 4
Loan Amount Sanctioned (Rs.75,000/- Rs.1,00,000/-) - - -.073 10
Loan Amount Sanctioned (Rs.25,000/- - Rs.50,000/-) .610 2 - -
Loan amount as cash (Below Rs.10,000/-) - - .114 9
Loan amount as cash (Rs.10,000 - Rs.40,000/-) .556 3 - -
Loan amount as seed (Rs.5,000/- and above) - - .178 8
Loan amount as seed (Rs.1,000/- - Rs.3,000/-) .431 4 - -
Loan amount as fertilizer (Rs.7,000 - Rs.11,000/-) - - .255 7
Loan amount as fertilizer (Rs.3,000/- - Rs.7,000/-) .422 5 - -
Insurance (Rs.1,000 - Rs.1,500/-) .381 7 - -
Insurance (Not applicable) - - .415 5
Duration of loan (10 - 12 months) .404 6 - -
Duration of loan (6 - 10 months) - - .342 6
Earlier payment days (Not applicable) .073 10 .721 2
Period of delay (One year and above) .619 1 .543 3
Interest (Rs.1,000/- - Rs.4,000/-) - - .940 1
Interest (Rs.7,000 and above) .378 8 - -
Table 17 Impact of Hidden Layers on Farmers' Loan Repayment in Eragudi branch
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 -1.807 1.677
H2 -.350 -.212
H3 .900 -.575
H4 .379 .037
Bias -.091 -.194
Percent Incorrect Predictions - Training (0.0%), Testing (1.4%)
335
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table 18 Estimation of Parameters for PACCS branch of Eragudi
Best Hidden Layer
Predictors Hidden Hidden
Rank Rank
Layer 1 Layer 2
Crop Name (Paddy) .325 5 - -
Crop Name (Banana) - - .448 6
Loan Amount Sanctioned (Rs. 50,000/- - Rs.75,000/-) .302 6 - -
Loan Amount Sanctioned (Rs.25,000/- - Rs.50,000/-) - - .485 5
Loan amount as cash (Below Rs.10,000/-) .256 7 - -
Loan amount as cash (Rs.40,000 - Rs.70,000/-) - - -.093 9
Loan amount as seed (Rs.5,000/- and above) .135 9 - -
Loan amount as seed (Rs.3,000 - Rs.5,000/-) - - .376 7
Loan amount as fertilizer (Rs.11,000/- and above) .340 3 - -
Loan amount as fertilizer (Rs.3,000/- - Rs.7,000/-) - - -.143 10
Insurance (Rs.1,500/- and above) .141 8 .232 8
Duration of loan (10 - 12 months) .014 10 - -
Duration of loan (12 - 15 months) - - .559 2
Earlier payment days (Paid on due date) .337 4 - -
Earlier payment days (Not applicable) - - .489 3
Period of delay (Not applicable) .532 2 - -
Period of delay (One year and above) - - .489 4
Interest (Not applicable) .601 1 - -
Interest (Till unpaid) - - .612 1
Table 19 Impact of Hidden Layers on Farmers' Loan Repayment in Venkatesapuram branch
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 -4.335 4.118
Bias -.118 .183
Percent Incorrect Predictions - Training (0.0%), Testing (0.0%)
Table 20 Estimation of Parameters for PACCS branch of Venkatesapuram branch
Hidden
Predictors Rank
Layer 1
Crop Name (Paddy) .414 5
Loan Amount Sanctioned (Rs.50,000/- - Rs.75,000/- .300 7
Loan amount as cash (Rs.10,000 - Rs.40,000/-) .219 8
Loan amount as seed (Below Rs.1,000/-) .146 9
Loan amount as fertilizer (Below Rs.3,000/-) .387 6
Insurance (Not applicable) .101 10
Duration of loan (12 - 15 months) .466 4
Earlier payment days (Not applicable) .937 1
Period of delay (1 - 6 months) .472 3
Interest (Rs.1,000/- - Rs.4,000/-) .751 2
336
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table 21 Pooled Analysis on Impact of Hidden Layers on Farmers' Loan Repayment in PACCS
branches
Farmers' Loan Repayment Strategy
Hidden Layers
Prompt Payer Defaulter
H1 .236 -1.011
H2 -.410 -.131
H3 -.975 .885
H4 .036 -.409
H5 -.808 .686
H6 .959 -.492
H7 .882 -.292
H8 .648 -.899
H9 .308 .010
Bias -.348 .271
Percent Incorrect Predictions - Training (0.3%), Testing (0.0%)
Table 22 Estimation of Parameters for PACCS branches
Best Hidden Layer
Predictors Hidden Hidden
Rank Rank
Layer 6 Layer 3
Crop Name(Paddy) .013 10 - -
Crop Name(Banana) - - .346 4
Loan Amount Sanctioned(Rs.75,000/- - Rs.1,00,000/- .324 6 - -
Loan Amount Sanctioned(Below Rs.25,000/-) - - .038 8
Loan amount as cash(Below Rs.10,000/-) .122 8 .335 5
Loan amount as seed(Rs.5,000/- and above) .283 7 - -
Loan amount as seed(None) - - .071 7
Loan amount as fertilizer(Below Rs.3,000/-) .532 1 .015 9
Insurance(Rs.1,500/- and above) .084 9 - -
Insurance(Not applicable) - - .266 6
Duration of loan(10 - 12 months) .433 4 - -
Duration of loan(12 - 15 months) - - -.025 10
Earlier payment days(Paid on due date) .434 3 - -
Earlier payment days(Not applicable) - - .857 1
Period of delay(Not applicable) .469 2 - -
Period of delay(One year and above) - - .700 2
Interest(None) .373 5 - -
Interest(Rs.4,000/- - Rs.7,000/-) - - .437 3
5. FINDINGS
Table 1 reveals that in Eragudi branch, major borrowers are male and the age group of farmers
those who obtained loan are of above 50. Most of the farmers has annual income of Rs.75,000/- to
Rs.1,00,000/- and they have their family size between 2 to 4 members. Majority of the farmers are
educated up to secondary level. In Singalandapuram branch, major borrowers are male and the age
group of farmers those who obtained loan are of above 50. Most of the farmers has annual income of
Rs.75,000/- to Rs.1,00,000/- and they have their family size between 2 to 4 members. Majority of the
farmers are educated up to secondary level. In Venkatesapuram branch, major borrowers are male and
the age group of farmers those who obtained loan are of above 50. Most of the farmers has annual
income of Rs.50,000/- to Rs.75,000/- and they have their family size between 2 to 4 members. Majority
of the farmers are educated up to secondary level. To visualize the overall analysis, it states that major
borrowers are male and the age group of farmers those who obtained loan are of above 50. Most of the
farmers has annual income of Rs.50,000/- to Rs.75,000/- and they have their family size between 2 to 4
members. Majority of the farmers are educated up to secondary level.
337
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
Table 2 reveals that in Eragudi branch, majority of the farmers are small farmers and they own
land of 1 to 3 acres. The major group of farmers crop paddy and they have been sanctioned loan below
Rs.25,000/- and they received loan amount as cash of Rs.10,000/- to Rs.40,000/-, as seed Rs.1,000/- to
Rs.3,000/-, as fertilizer Rs.3,000/- to Rs.7,000/- and for insurance below Rs.500/-. Most of the farmers'
cultivation period is between 6 to 10 months. In case of earlier payment days, major group of farmers
do not repay the loan before due date but they have paid on due date so delay is not applicable and they
need to pay interest. Finally, majority of the farmers are prompt payers. In Singalandapuram branch,
majority of the farmers are small farmers and they own land of 1 to 3 acres. The major group of
farmers crop paddy and they have been sanctioned loan below Rs.25,000/- and they received loan
amount as cash of Rs.10,000/- to Rs.40,000/-, as seed Rs.1,000/- to Rs.3,000/-, as fertilizer Rs.3,000/-
to Rs.7,000/- and for insurance below Rs.500/-. Most of the farmers' cultivation period is between 6 to
10 months. In case of earlier payment days, major group of farmers paid the loan 30 days before due
date but they have paid on due date and delay is not applicable hence they need to pay interest. Finally,
majority of the farmers are prompt payers. In Venkatesapuram branch, majority of the farmers are
small farmers and they own land of 1 to 3 acres. The major group of farmers crop paddy and they have
been sanctioned loan between Rs.25,000/- to Rs.50,000/- and they received loan amount as cash of
Rs.10,000/- to Rs.40,000/-, as seed Rs.1,000/- to Rs.3,000/-, as fertilizer Rs.3,000/- to Rs.7,000/- and
for insurance below Rs.500/-. Most of the farmers' cultivation period is between 6 to 10 months. In
case of earlier payment days, major group of farmers do not repay the loan before due date but they
have paid on due date, so delay is not applicable hence they need to pay interest. Finally, majority of
the farmers are prompt payers. To view from the overall analysis of famers, it is found that majority of
the farmers are small farmers and they own land of 1 to 3 acres. The major group of farmers crop
paddy and they have been sanctioned loan below Rs.25,000/- and they received loan amount as cash of
Rs.10,000/- to Rs.40,000/-, as seed Rs.1,000/- to Rs.3,000/-, as fertilizer Rs.3,000/- to Rs.7,000/- and
for insurance below Rs.500/-. Most of the farmers' cultivation period is between 6 to 10 months. In
case of earlier pa days, major group of farmers do not repay the loan before due date but they have paid
on due date, so delay is not applicable hence they need to pay interest. Finally, majority of the farmers
are prompt payers.
Table 3 reveals that in Singalandapuram, the variables like educational qualification, land owned,
and number of family members helps in having a best prediction of repayment on farmers' loan. Table
4.5 reveals that in Singalandapuram, the factors like land owned, nature of farmer, and annual income
contribute for the prompt payment of the farmers. The reasons for being a default payer is due to
factors like educational qualification, nature of farmer and annual income. Table 6 reveals that in
Eragudi, the variables like educational qualification, age, and number of family members helps in
having a best prediction of repayment on farmers' loan. Table 8 reveals that in Eragudi, the factors like
educational qualification, age, and annual income contribute for the prompt payment of the farmers.
The reasons for being a default payer is due to factors like nature of farmer, educational qualification,
and age.
Table 9 reveals that in Venkatesapuram, the variables like number of family members, land owned
and annual income helps in having a best prediction of repayment on farmers' loan. Table 11 reveals
that in Venkatesapuram, the factors like family members, annual income, and land owned contribute
for the prompt and default repayment of the farmers. Table 12 reveals that in Singalandapuram,
Eragudi, and Venkatesapuram, the variables like number of family members, educational qualification,
and age helps in having a best prediction of repayment on farmers' loan.Table 14 reveals that in
Singalandapuram, Eragudi, and Venkatesapuram the factors like land owned, annual income, and
educational qualification contribute for the prompt payment of the farmers. The reasons for being a
default payer is due to factors like educational qualification, number of family members, and gender.
Table 16 reveals that in Singalandapuram, the factors like period of delay, loan amount sanctioned,
and loan amount as cash contribute for the prompt payment of the farmers. The reasons for being a
default payer is due to factors like interest, earlier payment days and period of delay. Table 18 reveals
that in Eragudi, the factors like interest, period of delay, and loan amount as fertilizer contribute for the
prompt payment of the farmers. The reasons for being a default payer is due to factors like interest,
duration of loan, and earlier payment days. Table 20 reveals that in Venkatesapuram, the factors like
earlier payment days, interest, and period of delay contribute for the prompt and default repayment of
the farmers. Table 22 reveals that in Singalandapuram, Eragudi, and Venkatesapuram the factors like
loan amount as fertilizer, period of delay, and earlier payment days contribute for the prompt payment
338
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
of the farmers. The reasons for being a default payer is due to factors like earlier payment days, period
of delay, and interest.
6. SUGGESTIONS
SINGALANDAPURAM BRANCH
The banker may have a prompt payer when they lend the loan amount to the farmers those who are
coming under the following criteria such as the land cultivated by them is of 5 acres and above and the
farmers with an annual income of Rs.1,00,000/- and above, the loan amount sanctioned is between
Rs.25,000/- to Rs.50,000/-, as cash when it is provided Rs.10,000/- to Rs.40,000/-, as seed when it is
provided Rs.1,000/- to Rs.3,000/- . The banker may get a delayed payment from the farmers when they
are educated below secondary level of education, they own land of 5 acres and above with the annual
income of Rs.1,00,000/- and above. The farmers who pay interest of Rs.1,000/- to Rs.4,000/-, who do
not pay on or before the due date, and the farmers who cropped paddy mostly fail to make the prompt
payment. It is suggested to the bankers to consider these factors and sanction the loan to the farmers.
ERAGUDI BRANCH
The banker may have a prompt payer when they lend the loan amount to the farmers those who are
coming under the following criteria such as the farmers who are educated at primary education level,
coming under the age group of 40 to 50, with an annual income of Rs.50,000/- to Rs.75,000/-, interest
and delay for payment is not applicable, and loan amount sanctioned as fertilizer when it is provided
Rs.11,000/- and above . The banker may get a delayed payment from the farmers when they own land
of 5 acres and above, they do not have formal education, and when they come under the age group of
40 to 50. The farmers who do not pay both the interest and capital, who have the cultivation period of
12 to 15 months, and who do not pay before the due date mostly fail to make the prompt payment. It is
suggested to the bankers to consider these factors and sanction the loan to the farmers.
VENKATESAPURAM BRANCH
The banker may have a prompt payer when they lend the loan amount to the farmers those who are
coming under the following criteria such as the farmers whose number of family members is between 5
to 7 people, with an annual income of Rs.1,00,000/- and above, and the farmers who own land of 3 to 5
acres. The banker may get a delayed payment from the farmers when they earlier payments days are
not applicable, pay interest of Rs.1,000/- to Rs.4,000/-, and the farmers who delay 1 to 6 months mostly
fail to make the prompt payment. It is suggested to the bankers to consider these factors and sanction
the loan to the farmers.
7. CONCLUSION
Each and every bank face the problem in recovery of loan amount on or before due date that is given to
their loan receivers. This research is focused on identifying the factors that influence in making the
payment by the loan receiver. The research is made on the repayment of loan amount by the farmers of
Primary Agricultural Cooperative Credit Society in the branches Singalandapuram, Eragudi, and
Venkatesapuram. The result of neural network analysis of personal and demographic factors such as
gender, age, annual income, educational qualification, number of family members, nature of the farmer,
and land owned shows that well educated people with an age group of 20 to 30 make a prompt payment
of the loan amount where as farmers with secondary level of education and with a family size of 2 to 4
and those whose farm size is small which is below 2.5 acres fail to make repayment on or before due
date. The result also shows that there are more male farmers make a delayed payment, this is due to the
relaxed attitude that a male has. The neural network analysis of different variables brings off the
following information that farmers who receive part of loan amount as seed of Rs.5,000/- and above,
the farmers with loan duration of 10 to 12 months make prompt payment without any delay. Lower
interest and penalty rates induce the farmer to make delayed payment, and the farmers who cropped
banana failed to be a prompt payer. Apart from the suggestions derived from the analysis made some
other reasons were found responsible for a delayed payment. The reasons are crop failure, unusual rain,
low productivity of crop, unexpected expenses in family and friends, investing loan amount in assets
such as land, house, jewels, etc. The banker will get benefitted when they sanction the loan by
339
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
- International Journal of Management (IJM), ISSN 0976 – 6502(Print), ISSN 0976 -
6510(Online), Volume 7, Issue 2, February (2016), pp. 326-340 © IAEME Publication
considering the suggestions given. The study also gives individual suggestions to all the three PACCS
branches
REFERENCES
[1] C J Arene and G C Aneke (1999), The Position of Women in the Repayment of
Agriculture Loans in Nigeria: An Analysis, Vikalpa, Vol. 24, No. 4, October-December
1999, PP 29 - 34.
[2] MC Mashatola& MAG Darroch (2003), Factors affecting the loan status of sugar-cane
farmers using a graduated mortgage loan repayment scheme in kwazulu-natal, Agrekon,
Vol 42, No 4 (December 2003), PP 353 - 365.
[3] Limsombunchai, V. C. Gan and M. Lee (2005), Lending Decision Model for Agricultural
Sector in Thailand, Department of Economics, American University of Sharjah, UAE, PP
573 - 579.
[4] AbebeMijena (2011), Determinants of Credit Repayment and Fertilizer Use By
Cooperative Members in Ada District, East Shoa Zone, Oromia Region, Haramaya
University.
[5] Ifeanyi A. Ojiako1 and Blessing C. Ogbukwa (2012), Economic analysis of loan
repayment capacity of smallholder cooperative farmers in Yewa North Local Government
Area of Ogun State, Nigeria, African Journal of Agricultural Research Vol. 7(13), pp.
2051-2062.
[6] J. A. Afolabi (2010), Analysis of Loan Repayment among Small Scale Farmers in Oyo
State, Nigeria, Kamla-Raj 2010 J SocSci, 22(2): 115-119.
[7] Henry De-Graft Acquah and Joyce Addo (2012), Socio-Economic Determinants of Rice
Farmers’ Loan Size in Shama, Ghana, American-Eurasian J. Agric. & Environ. Sci.,
IDOSI Publications, 12 (4): 516-520.
[8] Amjad Saleem, DrFarzand Ali Jan, and Rasheed Muhammad Khattak& Muhammad
Imran Quraishi (2011), Impact of Farm and Farmers Characteristics On Repayment of
Agriculture Credit, Abasyn Journal of Social Sciences; Vo. 4 No.1, PP 23 - 35.
[9] Mohammad Reza Kohansal and HoomanMansoori (2009), Factors Affecting on loan
Repayment Performance of Farmers in Khorasan-Razavi Province of Iran, Tropentag
2009, University of Hamburg, October 6-8.
[10] Victor UgbemOboh and Ineye Douglas Ekpebu (2011), Determinants of formal
agricultural credit allocation to the farm sector by arable crop farmers in Benue State,
Nigeria, African Journal of Agricultural Research Vol. 6(1), pp. 181-185.
[11] Yasir Mehmood, Mukhtar Ahmad, and Muhammad BahzadAnjum (2012), Factors
Affecting Delay in Repayments of Agricultural Credit; A Case Study of District Kasur of
Punjab Province, World Applied Sciences Journal 17 (4): 447-451.
340
Dr. G.S. David Sam Jayakumar and J.Sathyamurti, “Modelling The Prediction of Farmers' Loan
Repayment In Primary Agricutural Co-Operative Credit Societies” – (ICAM 2016)
nguon tai.lieu . vn