Mathfi-Finance
Log in/Register Request a Demo Instruction Manual
A new AI-powered service helping your decision experts to make binary and multi-class financial decisions by performing binary or multi-class predictions and classifications or sanity checking their existing predictions/classifications for example:
1. Improve the quality of credit scoring-based decisions by predicting the probability that a borrower will experience financial distress in the future: Knowing thousands of past borrowers’ data features including gender, job, monthly income, criminal records, house value, car model, address, age, total balance on credit cards and personal lines of credit except real estate and no instalment debt like car loans divided by the sum of credit limits, living costs divided by monthly gross income, number of open loans (instalment like car loan or mortgage) and lines of credit (e.g. credit cards), number of times borrower has been 90 days or more past due, number of mortgage and real estate loans including home equity lines of credit, number of dependents in family excluding themselves (spouse, children etc.), and other relevant data features and also having verified and labelled whether each one of those past borrowers has experienced financial distress or not (the target and label of the prediction), predict whether a new borrower will experience distress or not (and with what certainty probability, the risk factor).
2. Vehicle loan default prediction: Having recorded data features of thousands of past customers including payment default in the first Equated Monthly Instalment (EMI) on due date, amount of loan disbursed, vehicle value, loan to value of the vehicle, branch where the loan was disbursed, vehicle dealer where the loan was disbursed, vehicle manufacturer, customer age, gender, family status, number of dependants, monthly income, monthly expenditure (if it is known), house owner, house value, credit score, district, employment type (Salaried/Self Employed), date of disbursement, district of disbursement, whether mobile no. was shared by the customer, if passport was shared by the customer, bureau score, bureau score description, count of total loans taken by the customer at the time of disbursement, count of active loans taken by the customer at the time of disbursement, count of default accounts at the time of disbursement, total principal outstanding amount of the active loans at the time of disbursement, total amount that was sanctioned for all the loans at the time of disbursement, total amount that was disbursed for all the loans at the time of disbursement, count of total loans taken by the customer at the time of disbursement, count of active loans taken by the customer at the time of disbursement, count of default accounts at the time of disbursement, total Principal outstanding amount of the active loans at the time of disbursement, total amount that was sanctioned for all the loans at the time of disbursement, total amount that was disbursed for all the loans at the time of disbursement, EMI amount of the primary loan, EMI amount of the secondary loan, new loans taken by the customer in last 6 months before the disbursement, loans defaulted in the last 6 months, credit cards defaulted in the last 6 months, mortgage payment defaulted in the last 6 months, average loan tenure, time since first loan, number of enquiries done by the customer for loans, and having correctly verified and labelled whether those past customers have defaulted or not (target of prediction), then for a new or existing customer predict whether the customer is going to default in future or not (and with probability and certainty).
3. More reliable data-driven customer credit rating classification: Knowing the past customers’ data features such as car, spending, income, mortgage, house value, etc, and knowing that they have been correctly classified to the four credit rating buckets of (A, B, C or D), classify a new or existing customer into one of those four credit rating buckets of (A, B, C or D).
4. Predict if your customer will churn and leave your bank or financial organization before it happens to take preventing and preempting actions: Knowing the past customers’ data features such as number of app visits, number of bank branch visits, car brand, spending, income, mortgage, house value, etc, and knowing whether those customers have churned and left current financial organisation (e.g., a bank) or not, predict/decide whether a new or existing customer will also churn joining a competitor bank or not for example in a year time.
and any other binary or multi-class financial classification or prediction use cases.