Credit Scoring Vs Personalised Lending

In India, all banks have internal credit scoring models and it has not helped them in lending to SMEs.

Two key reasons why banks (formal lending institutions) do not lend to SMEs in India are
a.) Lack of information on actual profitability/cash flows. No official documented evidence of income can be found. This is primarily in keeping with practice of dealing in cash, belief in oral contracts and mostly absence of contracts (sale/purchase) altogether. In addition, the myopic tendency to avoid taxes leads to minimal documentation or under-reporting of incomes. If no concrete data is found, what do the bank feed into their credit scoring models?

b.) Small ticket size and hence high operating expense per loan. Ideally a credit scoring model reduces the high opex of small loans by taking an automated call on whether to do a loan or not without having a credit person go through the case in detail as he is expected to do in larger loan ticket sizes. But, then, for these kind of small loans with no concrete data, what does one feed into the credit scoring model? Subjective evaluations of the credit appraising officer?

It is undisputed that the effectiveness of a credit scoring model is dependent upon the quality of data being fed. However, since the quality/reliability of data that is available to be fed into the credit scoring model is poor and subjective, especially in case of SMEs in India, how does one use a credit scoring model? In fact, due to high level of subjectivity, the data being fed into the credit scoring model can jeopardise the credit scoring techniques.

Credit scoring models can speed up process but they can not replace personalized diligence based lending till the time good data is available. There is barely any electronic footprint left by SMEs that can be dug up for credit analysis. The bank account (if available) details wouldn’t show enough balance, their transactions would be fairly thin. Understood that visiting the customers for a small ticket size loan results in high opex but in the case of SMEs where transactions are primarily cash based, expecting to lend to customers in the SME segment without meeting the customers, suppliers, buyers of the SME and without visiting the location is a recipe for disaster.

A few new age lenders are depending upon use of surrogates/proxies for assessment of actual cash flows, followed by close monitoring of loans. They depend exceedingly on customer visits. Their portfolios have performed well but yes, it is too early. While it is not free of subjectivity, this approach seems to be better than that of large banks who use an inflexible credit scoring model based on documented data. I agree that the rate of growth in such kind of specialized lending may not be as fast as mainstream financial institutions till the time sufficient electronic footprint is generated by the target SMEs. Meanwhile, using some form of credit scoring models in parallel can add a layer of check over the existing rigorous personalized appraisal procedure. This helps in reducing the impact of subjectivity in the personalized lending processes.

Credit scoring models are needed. The critical question that we need to answer today is, how do we improve the quality of data available to be fed into credit scoring models? If not immediately, how do we build the right data backend that provides high quality data in the future?

According to me, this kind of data backend will have two components, one that deals with general data points which can be used for bench marking and two that deals with individual specific data points that further become a part of the general database:

a.) Benchmarking: A good data backend can actually be a like a platform where location specific details on various businesses and margins are fed by staff of lenders. Over a period of time and volume, these numbers will give adequate guidance on the claims of margins/profitability made by the potential borrowers. Once the coverage of data collection efforts improve with time credit scoring models can play a better role.

b.) For individual evaluation: Individual credit/liability histories need to be pushed into this data back-end. Electricity bills, mobile phone bills, credit bureau details, need to be automatically fed or fed based on requests. The question is will the respective companies share data? Will a mobile company share prepaid recharge data of a customer?

Once this is done over a period of time, I believe a credit scoring model will start making more sense for SME lending in India. However, ditching personalized lending altogether, would continue being a distant dream for a fairly long time, if not for ever.

The approach can not be Credit Scoring VS personalized lending. The approach instead has to be Credit Scoring AND personalized lending.

Food Wastage: Challenges for India

A FAO study throws up interesting numbers on food wastage across the world and splits up food wastage per capita into supply chain losses and consumer level losses. For developed countries, consumer level wastage is alarming but for countries like India, the supply chain level wastage is alarming because of the volume of food losses given the country’s size and the scale of its farm output. India is not unique in the level of its losses. According to the FAO,42 per cent of fruit and vegetables grown in the Asia-Pacific region, and up to 20 per cent of the grain, never reaches consumers because of poor post-harvest handling.

I think there are two key reasons why it is practically more difficult to reduce wastage in India, compared to the developed countries.

a.) Structural Challenge : It is important to note that supply chain issues (for agricultural produce) in India is much more complicated and difficult to sort out compared to North America and Europe, primarily because of structural differences in production. Indian agriculture is primarily small holder agriculture and hence disaggregated by nature. However, it is also said that the milk supply chain has done comparatively better than vegetables when it comes to reducing wastage. One of the key reasons behind that is structural “innovations” at the farmer level for aggregation i.e. pockets of successful co-operative institutions. While investments in cold chain infrastructure is key, India has to find ways of improving aggregation at the farmer levels and unless that is in place we will not find people making extensive investments in cold chain infrastructure even after the policy situation has improved.

b.) Political Intent: A closely linked reality behind “private” sector not being able to do much in setting up efficient procurement back-ends (and marketing linkages in general till date), is that the farmers are a “constituency” of the politicians and to ensure that politicians continue to get votes,it is critical to ensure that farmers continue to depend upon politicians or continue to have expectations from politicians for critical needs. If the politicians enable the cold storage investment environment too much in favour of private entities, the private enterprises, which have historically shown better effectiveness, might make a dent on the dependence of farmers on politicians. This is not a happy state for the vote hungry political class. To put things in perspective, the politicians (as lawmakers) have the tough task of ensuring that policies do not breed exploitation of the weak by the strong and they do need to be sure of the intent of the people who look at investment in procurement infrastructure from a return on investments perspective. However, an equally pertinent question is if “partial” socialism helps us in the long run.

While I wanted to cover this in a separate post, I thought I might as well place it here to give a complete picture of the complications around deciding upon policies and the seriousness around that.

A few years ago, a nation-wide study on assessment of harvest and post-harvest losses for 46 different agricultural commodities was carried out in 106 randomly selected districts. The study was carried out by CIPHET, Ludhiana and the figures of wastage are much lower than any estimate we get from other reports or what we hear from even the policymakers. The wastage levels as per that report is given below.

Cereals 3.9 – 6.0 per cent, Pulses 4.3-6.1 per cent, Oil seeds 2.8-10.1 per cent, Fruits & Vegetables 5.8-18.0 per cent, Milk 0.8 per cent, Fisheries (Inland) 6.9 per cent,Fisheries (Marine) 2.9 per cent, Meat 2.3 per cent, Poultry 3.7 per cent.

These numbers have been used as a justification to stop FDI in market linkage in India with the argument that the level of losses in India is not much. Well! that is how complicated policy making is.

(Also published on LinkedIn.)

Will de-listing of Fruits & Vegetables from APMC Act affect price?

Recently, the Indian Central Government requested all State Governments to delist fruits and vegetables from the Agriculture Produce Market Committees Act (APMC Act). This was to address rising price in fruits and vegetables. I was trying to understand how this would affect things going forward. A basic analysis of what I think is going to happen is given below.

Currently, the APMC Act makes it mandatory for farmers to sell their produce only to licensed merchants at mandis set up by state agriculture marketing boards. So, it is being said that delisting will eliminate these licensed merchants or middlemen who set up a cartel and raise the prices for super normal profits. So, farmers will now be able to sell directly to retailers or food processors and hence the buyers will get fruits and vegetables at a lower price.

In addition, commissions earned by the agents, mandi tax, octroi, VAT or sales tax and inter-state movement charges add to the price of fruits and vegetables. Delisting from APMC Act would enable sale of fruits and vegetables to happen without payment of commissions, mandi tax/cess. This means that delisting would certainly wipe out state revenues from mandi tax/cess and potentially reduce price but will it enable farmers to sell directly to consumers/buyers and avoid traders/commission agents?

Does the farmer sell at the APMC market even today? The Planning Commission says that 75% of farmers sell their produce at the farmgate to traders, aggregators and sometimes contract buyers. In earlier initiatives taken in Bihar or even Andhra Pradesh and a few other states, doing away with APMC Act restrictions or setting up of Farmer Markets have not been able to eliminate middle men completely and that is due to practical issues. It is mostly the aggregators or agents who take farmer certificate and sell under their name in the farmer market. For the sake of convenience, a group of farmers generally find somebody from the village and sell their produce to him and he gets a license to operate in this market as a “farmer”. This is to arrive at a commercially viable and practical aggregation volume for transportation and time saving.

This means that under current situation, farmers are not reaching the APMC mandi anyways because of practical difficulties. How will they reach the consumer directly now when the fruits and vegetables have been delisted?They will need intermediaries or they will need consumers to reach out to them directly. Consumers will not be able to reach farmers directly. Fact is, they will need intermediaries, be it the local aggregators or the corporate retailers/buyers.

Question is, how do you ensure that the intermediaries do not form a cartel that jacks up prices for buyers once again? Will this deregulation reduce strength of cartels or lead to an increase in their power? In the past, states have delisted fruits and vegetables but haven’t succeeded in breaking cartels. So it is unlikely that cartels will get demolished just by delisting. The cartel will weaken only when alternate channels are built to enable competition. Delisting enables corporate buyers to buy directly without having to depend upon intermediaries or having to enroll at the mandi and having to pay mandi cess. So, this will increase competition (at the cost of state revenues) but how will they reach farmers immediately? It is obvious that It is not going to immediately cool off the prices and it needs long term efforts in addition to just delisting. Unless multiple mutually independent market players enter the market, the pains of having to deal with high price will continue.

Another key component of the high price is spoilage that happens due to lack of appropriate cold chain facilities and change of multiple hands. So, it is important that this delisting initiative is followed by building physical infrastructure and competitive markets.

Such infrastructure has to be built by both private and public resources. Through policy stability and direction, large corporate buyers will now be encouraged to set up procurement networks deep into producing locations. It is also important that the state continues to provides alternate channels to farmers by building cold chain and storage facilities and supporting development of multiple options of storage and sale. Unless this is done, the corporate buyer may form one more cartel.

Let’s face it. Farmers will not reach retailers or consumers directly. We will need intermediaries, be it local aggregators or corporate buyers. We have to take steps to improve efficiency in movement of fruits and vegetables through these intermediary channels to ensure quality at the right price.

It is easier said than done. Delisting of fruits and vegetables is the first, easy to implement step (though politically difficult). It must be followed by a series of difficult to implement steps that promote appropriate infrastructure to improve efficiency and ensure availability of fruits and vegetables at the right price. Hopefully, after paying the appropriate mandi taxes. 

What do you think?

Payments in remote locations

Payments to dairy farmers in residing in rural remote locations is made primarily in cash across India. Every week/fortnight, the milk collection van brings in a cash box and pays the farmers the price of milk bought since the last payday. In some cases, the payment is daily.

Experience revealed that in making payments to farmers through this route, the cashier handing over the cash often held back some amount of money as a “commission” or out of plain rowdyism. The cashier/ accountant would in a lot of cases be the favourite man of the secretary of the collection centre (society) or the secretary himself. The helpless farmer would then have to part with a fraction of the money due to him to make sure s/he doesn’t rub the powerful cashier the wrong way.

Some milk buying companies thought of a novel way of eliminating this problem. They started paying the money directly to the bank account of the farmer. The bank account was especially opened for this purpose. So, the cashier is no longer able to play foul. But, on every payday, the farmer has to abandon work (which means loss of a day’s wage or agriculture) and go to the bank branch which would be in a “nearby” town, some 15-20 kms away. He incurs travel expenses as well. The money has to be drawn out immediately because the farmer needs the cash to buy daily items like groceries, medicines, etc. There is no other source of cash income that is as regular/frequent as dairy. Moreover, much to the disgust of the bank manager in the town, there would be a long queue of dairy farmers waiting to draw their money on every payday leading to a tremendous rush in an otherwise quiet (and understaffed) bank branch.

The innovative milk buying companies understood this problem as well and figured out a solution. They handed over bio-metric cards to the dairy farmers for each bank account and got an “agent” tied to a third-party payments company to hand deliver the cash at the doorstep of the farmer. The agent carried bags of cash to the village and after bio-metric authentication hands the cash over to the farmer at the doorstep. But then, after a few months the agent starts charging commission, lesser than the cashier/secretary in the first situation but charges some amount. The bio-metric account reads that the farmer has drawn the entire amount of money. Though this agent works with a “private” company with greater accountability, the farmer agrees to let go of the amount because otherwise he will have to travel all the way to the bank.

We are back to square one and possibly in an even worse situation. In the earlier case, the cash was sent to the remote village in a milk truck with at least two persons on board. Not an ideal situation but it was better than what we see in this system. In this system, the “agent” typically hops on to a motorcycle with the bag of cash picked from a local bank branch and rides all the way to the villages. A few agents get robbed on the way. In fact carrying a few lakhs of cash does not turn out to be a safe thing to do. But there is no other way. Cash in transit insurance saves the day for some milk buying companies but some agents get killed.

Where does this end? “Mobile money” some people say. However, till the time the local grocery shops start accepting payments through mobile phones, how will mobile money transfer be of any use?

How have these risks been handled in India and outside? What are the examples of payments in remote locations seen in other parts of the world? What kind of supporting infrastructure is required to enable a safer payments situation?

(Also published on LinkedIn.)


Elevators permitted increases in height of buildings. In other words, density of people living per square km could go up because elevator permitted multiple floors and hence more people.

More people per square km means that a much larger number of people are using the same available space of roads to move around. Congestion.

What do you do?

a.) Wish that elevators were not invented and instead of vertical growth, the cities would grow horizontally and that instead of pockets of highly developed cities you had continuous stretches of several small cities with mid sized buildings and less congestion on the road due to lower population density.

b.) Wish that somebody invents private-individual flying cars quickly and the somebody also builds lanes of air traffic with different lanes for different levels (heights) paying different charges.



Renewable Energy.


Medical Technologies. (Detection and treatment)

Agriculture.- Food production & Food preservation.

That is where breakthrough innovation is required. We will possibly see breakthrough innovations in these areas (in that order) in future. Something similar to what we have seen in case of communication technologies over the past decade.

While Renewable Energy and Medical Technologies have received venture investments, Agri-Tech and Water are still to see mainstream venture capital investments.