AI, data mining, and machine learning – Juris Mindcraft • JurisTech

What is Juris Mindcraft?

Juris Mindcraft is an automated Machine Learning (autoML) and artificial intelligence (AI) platform that uses advanced machine learning (ML) techniques to build powerful AI models. An effortless AI that enables enterprises especially banks and financial institutions to make intelligent business decisions and gain insights to solve real-world problems.

Why Juris Mindcraft?

Explainable AI

Explainable models and decisions that help you understand and interpret predictions.

Easy Deployment

AI models deployed as RESTful service eliminating the discrepancy between different programming languages used by data scientists and software engineers.

Uses the best of multiple algorithms

Creates a supermodel that is more robust, less prone to overfitting, and outperforms any single best-performing ML model.

Continuous learning to maintain relevance

Automatically maintains all of your production models at peak performance regardless of changing conditions.

Operationalises AIOps

A set of capabilities that focuses on operationalising the full life cycle management of all AI and decision models.

How does Juris Mindcraft work?

Our end-to-end AI platform covers data pre-processing, machine learning modelling, all the way to deployment. Juris Mindcraft allows you to train and build powerful machine learning models at scale and use your model to make predictions and intelligent business decisions effortlessly.

Juris Mindcraft supports both supervised learning problems, namely, classification and regression. It also supports explainable models and decisions, on top of, RESTful service deployment of AI models to production systems. This breaks down the walls of confusion between data scientists, software engineers, IT teams, and business decision makers for better coordination and faster deployment.

1. Load Data

Drag and drop the dataset
Choose the correct model metrics
Score models

2. Data Pre-processing

Feature engineering
Feature selection
Feature transformation
Data encoding
Missing values
Outlier handling
Check variable types

3. Modeling

Select algorithms
Tune hyperparameters
Select top models
Model stacking

4. Evaluation

Evaluation metrics
Plots and charts
Model comparison
Business value analysis
Life analysis
Champion challenger

5. Deployment

Implements in the application
Converts into languages suitable for production
Test
Rest API

6. Monitoring

Maintains performance and reliability SLAs
Detects decline in model performances over time
Rebuilds the model in response to changing conditions

Continuous Learning

Juris Mindcraft continuously learns to maintain relevancy to deliver exceptional results despite unforeseen conditions. Continuous learning allows a deployed model to automatically update and improve itself whenever new data gets fed into it. When a model goes live, Juris Mindcraft will track the performance of the model overtime. If there is a sign of decline in performance, Juris Mindcraft will automatically update the model in response to the changing conditions. Hence, a deployed model with the same goal can be used over years without having to replace it.

AutoML Use Cases for the Financial Industry

Triggers early warning system to forecast non-performing loans (NPLs)

Challenge

Non-performing loans (NPLs) are a prevalent issue for both lender and borrower. A bank loan is considered non-performing when more than 90 days pass without the borrower paying the agreed instalments or interest. Most banks address this issue by automating the collections process. However, the automated processes are not flexible enough to recognise the patterns of customer behaviour. Therefore, banks are unable to identify NPLs and even prepare for them.

Solution

Juris Mindcraft forecasts the future performance of loan accounts and detects potential NPL accounts based on the five C’s of credit (character, collateral, capacity, condition, and conduct of the loan accounts). This enables banks the flexibility to pivot and take precautionary measures and actions on the potential NPLs through sets of treatment strategies that can be configured based on business requirements.

Utilise self-curing prediction strategy to approach delinquent customers

Challenge

It is common that collectors are not able to approach all delinquent customers due to a large number of cases. In addition, each customer and their circumstances are unique. Collectors would need to be able to recognise the different groups of at-risk customers, based on their ability and willingness to pay. The challenge is to find the right collection strategies and actions to avoid calling low-risk customers who will eventually self-cure, and also, to be careful to not alienate potentially profitable customers who might be going through a temporary stage of financial hardship.

Solution

Self-curing is a strategy that provides a grace period for customers to proactively pay off their outstanding balance before investing the organisation's resources to contact them to make a direct request for that payment. Self-curing predictions are assisted by a set of predictive rules generated by an artificial intelligence (AI) model. By using data mining and machine learning techniques, the AI model in Juris Mindcraft 'studies’ static and past behavioural information of accounts and makes predictions based on its learned experience. This allows collectors to focus on customers with higher probability of defaulting. Collectors can then use low-cost channels such as calls and text to reach customers with less risk. With this approach, collectors can reduce both the cost of collections and the volume of loans to be resolved through restructuring, sale, or write-off.

Identifies credit default risk when scoring customers

Challenge

The COVID-19 crisis has triggered specific implications from managing and mitigating credit risk. The risk of loss arising from a borrower being unlikely to pay its loan obligations in full or the borrower is more than 90 days past due on any material credit obligation may impact all credit-sensitive transactions, including loans, securities, and derivatives. Changes in creditworthiness differ by sector and subsector to a greater degree than they did in previous recessions. Hence, the ability to accurately identify credit risk during the scoring and loan approval stage is a huge challenge.

Solution

Juris Mindcraft uses Machine Learning modelling as a basis to better predict the potential risk and likelihood of a current loan defaulting. It’s AI-based algorithm helps crunch huge quantities of customer data in a few seconds to verify the customer’s creditworthiness and determine whether to grant a customer a loan. Juris Mindcraft enriches the credit risk management process by reducing time-to-market and ensuring accurate credit scores.

Utilise alternative credit scoring for the credit-invisible customers

Challenge

In traditional financial services, only those who are in the credit system will be given access to loans. However, people outside the credit system such as the unbanked, unserved, or underserved market would not qualify to access such services. This is because the banks have no way of assessing their creditworthiness due to the lack of traditional credit data/history.

Solution

Juris Mindcraft's Machine Learning model takes into account nontraditional data sources such as financial transactions, web traffic, mobile devices, and public records that can be used to assess the creditworthiness of an individual or a business without a credit history. Digital banks and Fintechs can leverage alternative data to expand their services to credit-invisible customers to increase market reach. This more granular and individualised approach also allows banks and financial institutions the ability to more accurately assess each borrower and allows them to provide credit to people who would have been denied under the traditional scorecard system.

Predicts next best actions to accelerate the origination and collection processes

Challenges

Industries have come to realise that every customer journey is unique. The challenge for origination and collection officers are to find the right set of actions for an individual that will move them to the next step in guaranteeing a loan or actions in collecting a bad debt.

Solution

Juris Mindcraft recommends the next best actions to origination and collection officers enabling them to make faster, more accurate, and automated decisions backed by data insights. Ultimately, Juris Mindcraft helps officers to build more meaningful interactions, taking corrective actions, and making offers that actually meet customer's needs.

Origination: Juris Mindcraft analyses the creditworthiness of customers. For credit-worthy customers, Juris Mindcraft will suggest officers to approve applications while the customers who are not credit-worthy, Juris Mindcraft will suggest officers to ask them for a bank guarantee.

Collection: Juris Mindcraft analyses if the customer is a bad paymaster. If the customer is predicted to be a bad paymaster, the next best action of aggressive treatment (SMS, calls, P2P) and suspension/termination warning will be suggested to the officer. Juris Mindcraft will suggest the officer to resolve disputes if the delinquency is due to customer dissatisfaction.

Optimises the customer acquisition cost in telemarketing

Challenges

Customer acquisition cost (CAC) is a key target for business, especially for telemarketers. It is important for a business to know each customer's valuation so they know how much of its resources they should spend on a customer so as to be profitable. Many contact centres struggle to prioritise tasks for agents and to make the best use of agents' time. Since there are only so many conversions you can have in a day, the ability to identify quality leads quickly will help agents work more efficiently plus increase customer satisfaction.

Solution

Implementing AI can help optimise your lead generation efforts and reduce your CAC. Juris Mindcraft makes use of the existing customer database to mine potential customers who could be approached or has high lifetime values. Juris Mindcraft improves and optimises your telemarketing efforts to reduce customer acquisition costs by sorting through hundreds of leads to find the customers most likely to want your services or products. This will enable your agents to engage and spend more time with high-quality leads increasing conversion and reducing the number of calls made.

Witness AI in Action

Create business moments with Juris Mindcraft by making intelligent business decisions.

Request Free Demo

Request Whitepaper(s)

Related Insights

JurisTech’s 2026 LLM Benchmark For AI Hallucination in Finance

By John Lim|2026-05-15T10:12:34+08:0014th May, 2026|

JurisTech’s 2026 LLM Benchmark examines AI hallucination in finance by testing whether leading large language models can recognise missing evidence, reject invalid questions, and avoid unsupported assumptions in banking and lending workflows.

Best LLM Tools for Financial Analysis 2026: JurisTech’s Hallucination Benchmark Report

By John Lim|2026-04-16T11:01:25+08:0015th April, 2026|

This is the benchmark report every CFO, analyst, and AI buyer in finance needs to read before choosing an LLM.

Bridging the Trust Gap with AI: JurisTech Champions Financial Inclusion at CIBI IMPACT 2025

By JurisTech|2025-08-21T16:31:17+08:0021st August, 2025|

At CIBI IMPACT 2025 in Manila, Philippines, JurisTech brought its vision for inclusive AI technologies to life. Through a compelling keynote, a live demo, and engagements with local financial leaders, the team showed how AI can drive fairer decisions, restore trust, and expand access to finance.