/From NY to DC

From London to NY and more

On my way to Washington from NY I finally have some time to sit down and process.

Sometimes myself  – and others with me – hated the choice of staring this start-up. And I must admit there were – and are – days that I really think .. what have I gotten myself in to.

The last two weeks have been the opposite. We have hired a CFO : FCA – Well needed ;-)

We will go live with the new website and before the years end we will sign three different test cases. And in Q1 hopefully a big financial institution will sign off, our valuation is getting back to the amount what we anticipated by the end of Q4 – validated by a big VC -  of this year and I feel we are finally getting the attention we deserve.

For those who don’t know what we do I will dive in and make this a bit technical – you can always scroll down ;-)

 __

VioScore™  for Loans

A loan distribution is a risky industry, but it is also one of the main revenue streams for the majority of banks.

Banks would rather not extend credit to clients that are unable to repay the borrowed funds. Nevertheless, despite the potential that banks tighten their lending policies – especially in 2022 with the new GDPR regulations - a certain proportion of credits will eventually turn into bad loans [i].

The percentage of the bad loans and the quality of the credit endorsement process can be efficiently assessed by analyzing the data on non-performing loans (NPLs).

The loan-granting procedure must be closely monitored, and banks must develop a strong credit risk management strategy.

In the majority of banking organizations, the department that evaluates loan applications uses a centralized process.

Using the banks' credit scoring model, introduction divides financing applications between risky and non-risky customers. The objective of this credit scoring procedure is to reduce the risk of loan losses and default rate due to the expensive misclassifying error. It will determine who should be awarded credit and how much credit should be granted.

Therefore, the risk generated increases in proportion to the size of the misclassifying error . Despite the extensive procedure and the potential for the bank's lending policy to tighten, after some time, a certain percentage of this will become bad credit.

Unsuccessful loans will eventually replace a percentage of the credits. This raises the question of whether the credit scoring model was efficiently built, especially in light of the choice of pertinent factors/variables for the model and the weights allocated to those variables in the model.

The bank management must thus reassess the current credit rating algorithm that it uses to screen loan applications.

Is it necessary to keep using the current model?

A revision of the model's criteria may be necessary. Does the model's weighting of the various criteria make sense? Exist any other more efficient and straightforward methods that could be used? Are the current used models adopted widely enough to the life in the 20th century?

At VioScore™ we belief that the base of an alround risk profile should always be credit, but we feel there is a need for a more rounded view of the consumer.

Reviewing the various credit scoring models and identifying the methods, brings us back to the first question. How are currently models working.

Techniques for Credit Scoring

Credit scoring methodologies can be classified into two categories:

1 - statistical-based methods

2 - machine learning/artificial intelligence-based methods

Models for Credit Scoring Based on Statistics

Numerous statistically based credit scoring models, including linear discriminant analysis

, decision trees, Markov chain analysis , probit analysis, and logistic regression  have been developed.

The linear discriminant analysis technique makes the assumption that there are two populations of people—designated as "1" for defaulters and "0" for non-defaulters—each of which is characterized by a multivariate distribution of a set of attributes, X, including elements like age, income, family size, credit history, occupation, and so on `.

The following is the formula for the linear discriminant analysis :

Z=α+β1X1 +β2X2 +.....+βnXn

where Z symbolizes the discriminant Z-score, α is the intercept term, β1 ... βn stand for coefficients in the linear combination of the explanatory variables for Xi for i = 1 ... n.

Linear discriminant analysis is one of the earliest common traditional statistical techniques used for constructing credit scoring models. However, this technique requires rather restrictive statistical assumptions that are seldom satisfied in real life.

We have a long white paper of the process above and what other elements – Based on the four quadrants of life, word & Maslovs hierarchy of needs we take into consideration. If you’re interested please drop me a note on romano@mylifekit.io

We at VisoScore. strongly believe that 2022 is ready for a credit score plus. Next to the three main ones we want to be the score with them to show the ultimate rounded model.

Now that we are almost a year old – I so remember the date of incorporation but that is a private story for hopefully another day when that circle is round again – it time to say I’m happy not to have given up, have shown resilience and persistence in diffent fields. And also finally make a clean slate. - more on that next week -

A company is like a marriage a friend of mine told me yesterday, you only know at the end how good was but the beauty of it lays in never giving up. That’s why not a lot of people succeed.

Interesting thought.

Off to learning the rules of grassroots and meetings with NAIC and more.. I guess its time to dress up .

Next stop Baltimore Penn Station.. almost in DC. .

 Romano.