Guide to Mitigating Credit Risk

Risk assessment is crucial for any enterprise that extends credit to customers. Commonly known as credit scoring, the process helps lenders make confident, informed decisions on whether prospective customers will honor their debt. Credit scoring is typically associated with the banking and financial service sectors, but is required across a wide array of businesses, including telecoms, retail, and insurance. In most cases, credit scoring isn’t just a business tool, it’s a regulatory necessity. And credit scoring is a vast industry. In the U.S. alone, recent consumer debt valuations hover over $14 trillion. Credit scoring is a complex task that involves wrangling a diverse range and large volume of data. Based on predictive modeling, the use of artificial intelligence (AI) and machine learning (ML) is well established and widespread. And because of the data burden, credit risk firms were some of the earliest organizations to adopt the technology. As such, the credit risk sector can claim to be a pioneer in AI and ML utilization.

Champion/Challenger Techniques Improve AI Performance

To successfully operationalize machine learning (ML) algorithms, data science teams must be able to continuously update their models so they can improve their predictive performance. The champion/challenger approach is a well-documented method for optimizing models and making adjustments that accounts for changes in the nature and quality of data inputs. Altair’s ML products make it easy to incorporate champion challenger processes into data analytics workflows.

Data Science for Engineers Series 2: Predictive Modeling and Evaluation

In the second installment of this Data Science for Engineering series, we covered:

• Predictive modeling and evaluation techniques
• The Cross-Industry Standard Process for Data Mining (CRISP-DM) framework
• Spotlight on Altair customer stories - Ford Motor Company and Renishaw
• Technical demonstration of building machine learning models for predictive maintenance, testing, and quality analysis
• Live Q&A Session
Webinars

Improve Efficiency and Profitability Accuracy of Mortgage Servicing Operations

Altair’s data analytics platform helps major banks and nonbank financial institutions transform the mortgage servicing process. Altair tools handle every phase of the data lifecycle, eliminate data silos, and provide decision-makers with excellent visibility into risk and profitability. Click here to explore high impact Altair Mortgage Data Solutions.

Weight of Evidence Node in Altair® Knowledge Studio®

Knowledge Studio’s Weight of Evidence node is essential to creating scorecard models. The Weight of Evidence node transforms your data so the model can assign points to every bin and these points will eventually add up to the scorecard. Knowledge Studio uses Altair’s patented decision trees to bin ordinal and some continuous variables. If the bins don’t make business sense, you can optimize them automatically by binning them for monotonicity and disallowing pure nodes. Knowledge Studio can optimize all variables in your dataset with a single click. You can also edit the splits if you have business reasons to bin your variables differently. Once Knowledge Studio has transformed your variables, you can see the code that created the transformation. Click here to learn more about Altair Knowledge Studio.

Ford Enhances Manufacturing Efficiency

Sheet metal stamping is fundamental to the automotive manufacturing industry. A vast array of different tool, die, and process combinations are employed to create an equally diverse array of components. Traditionally, identifying the optimum approach for each part has been a labor intensive and time-consuming task that requires engineering teams with high levels of skill and experience. This case study demonstrates how Altair Knowledge Studio, a general-purpose data analytics tool, can enable engineering managers and data analysts to deliver clear and quantifiable benefits in the manufacturing domain. For Ford, this is reflected in dramatic improvements in the speed and efficiency with which the best possible sheet metal stamping processes were selected.

Data Science for Engineers Series 2: Data Collection, Preparation, and Understanding

We kick off the Data Science for Engineering series by covering the first step of data science methodology. During this 90-minute presentation and Q&A we discuss:

• The "why" of engineering-data science convergence holds the key to unlocking the full potential of data and AI in manufacturing​.
• The data science basics including the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework​.
• How Mabe, a leader in home appliances, is leveraging the convergence of big data, analytics, and simulation to accelerate product innovation​.
• How you can gather, combine, structure, and organize engineering data using a self-service data preparation solution​ with a technical demonstration of Monarch.
Webinars

Real-Time Credit Scoring: Reduce Approval Times, Increase Loan Numbers, Improve Borrower Experience

Lenders need tools they can employ during the loan application process to advance an application to the next step or divert potential customers to alternative products that are a better fit. Implementing artificial intelligence (AI) models that facilitate fast credit reviews — and even approvals — can help lenders increase the quality, number, and amount of loans they grant without taking on unacceptable levels of risk.

Altair® Knowledge Studio® Advanced Machine Learning and Artificial Intelligence

Data scientists and business analysts use Altair to generate actionable insight from their data. Knowledge Studio is a market-leading easy to use machine learning and predictive analytics solution that rapidly visualizes data as it quickly generates explainable results - without requiring a single line of code. A recognized analytics leader, Knowledge Studio brings transparency and automation to machine learning with features such as AutoML and Explainable AI without restricting how models are configured and tuned, giving you control over model building. Watch this short demonstration video to learn more. Click here to learn more about Knowledge Studio.

Bank streamlines Collections with AI

A multinational financial services company wanted to explore improving its collection rate and process but did not have the in-house talent it could dedicate to the project. With billions in assets and more than 25 million customers throughout the world, the bank needed to integrate new sources of highly granular credit data with historical data from a variety of structured sources and semi-structured. Their collections process lacked prescriptive analytics to optimize which loan they reached out to each day and through which channel. It was also having productivity issues and struggling to launch new credit products because of inflexible data transformation tools that couldn’t accommodate new variables.

Machine Learning 101 Part 1: Predictive Analytics

This series of short videos will help you understand the basics of data science. In Part 1, we focus on predictive analytics, which is the process of training computers with historical data so they can make accurate predictions. Click here to learn more about machine learning.

Machine Learning 101 Part 2: Supervised Versus Unsupervised Learning

This is part two in a series of short videos to help you understand the basics of data science. This video focuses on the concepts of supervised and unsupervised learning. In supervised learning, you develop algorithms that predict outcomes based on independent variables and you use historical data to train your algorithms. Unsupervised learning models identify hidden patterns in your data and group records into clusters; they act on the dataset without human guidance. Click here to learn more about machine learning.

Machine Learning 101 Part 3: Prescriptive Analytics

This is part three in a series of short videos to help you understand the basics of data science. This video focuses on prescriptive analytics, which uses results from multiple machine learning algorithms to inform future decisions. With prescriptive analytics, the object is to optimize and, to some extent, automate the decision-making process. A prescriptive analytics workflow can use multiple algorithms to prescribe actions based on the characteristics of new data. Click here to learn more about machine learning.

Introduction to Altair® Knowledge Studio® 2022.0

Knowledge Studio 2022.0 introduces several important improvements that make the software easier than ever to use and deploy. Docker is no longer required to support any Knowledge Studio functionality, which makes deployments easier, eliminates certain compliance issues, and saves money. The software now offers a new decision tree tab and we have made enhancements to the SHAP tab and the decision tree tab provides a visual and easy-to-understand way to explain black box models. A single standardized scoring node is now applicable to all native models, ARIMA Forecasting, Keras Deep Learning, Novelty & Outlier Detector, GLM, and XGB models; this improves usability, simplifies the process of building workflows, and removes clutter from the Action function palette. Users can also now specify custom Python and R execution environments in the Python and R Code nodes, which allows them to use any version of Python or R with Knowledge Studio. Click here to learn more about Knowledge Studio.

Altair® Knowledge Studio®: Transparent AI and Machine Learning

Knowledge Studio, Altair’s machine learning and AI solution, quickly gets to the granular, low-latency data that contain the insights. Delivering transparency and automation with features such as AutoML and Explainable AI, we streamline model building so more time can be spent analyzing and results can be trusted. Our flexible no-code approach doesn’t restrict how models are configured and tuned, giving you control over model building. With our support for popular, open-source languages and engines, you can integrate new models built using Altair into your existing analytics infrastructure. Click here to learn more about Knowledge Studio.

ADAS - Introduction from a SYSTEMS and ML perspective

In an ADAS, high-performance CPUs are the central core for decision-making and other high-level system management. To enable various self-driving capabilities, highly powerful accelerators (DLA, GPUs etc) are used. In this talk, we will first focus on the various AI/ML-based ADAS tasks and the underlying hardware used to execute those tasks. The talk will also focus on the fault tolerance and robustness aspects of these systems. Finally, a brief discussion on how commercial software like Altair EMBED and KnowledgeStudio can be used in the domain.

Upload Machine Learning Models Built with Altair® Knowledge Studio® to Altair® SmartWorks™ Analytics

Knowledge Studio makes it easy to export models to Altair’s SmartWorks Analytics for model management and model deployment. This video was produced using Knowledge Studio 2021.3 and SmartWorks Analytics 2021.3.

Guide to Using Altair® RapidMiner® to Estimate and Visualize Electric Vehicle Adoption

Data drives vital elements of our society, and the ability to capture, interpret, and leverage critical data is one of Altair’s core differentiators. While Altair’s data analytics tools are applied to complex problems involving manufacturing efficiency, product design, process automation, and securities trading, they’re also useful in a variety of more common business intelligence applications, too. Explore how machine learning drives EV adoption insights - click here. An Altair team undertook a project utilizing Altair Knowledge Studio® machine learning (ML) software and Altair Panopticon™ data visualization tools to investigate a newsworthy topic of interest today: the adoption level of electric vehicles, including both BEVs and PHEVs, in the United States at the county level. This guide explains the team’s findings and the process they used to arrive at their conclusions.

Connected Products Deliver Big ROI

AI improves customer service and product quality for white goods manufacturer. Mabe manufactures home appliances, including stoves, refrigerators, washing machines, dryers, water purifiers, and more. The company is based in Mexico City and markets its white goods under its own brand as well as several others, including GE Appliances, in more than 70 countries. Mabe is an early leader in the development of connected products that allow its customer service personnel to monitor the health of its appliances in the field. Altair has been at the center of Mabe’s product development process for years, and Mabe is now working with Altair to deploy and enhance its connected products strategy. Learn more - click here to hear Martin Ortega, Senior Design Engineer at Mabe, explain how they are harnessing the power of big data, AI and simulation to accelerate product innovation.

Using Machine Learning to Fill Gaps in Large Datasets

One of the essential problems involved in managing large datasets is ensuring they’re complete. Many use cases, including materials databases, can use machine learning (ML) and artificial intelligence (AI) algorithms to accurately identify and fill gaps with data extrapolated from other data in the set. The datasets might contain time series data which, for example, may track the movement of components through a supply chain and/or static data like a parts inventory or test results. Altair’s data science tools are well suited to this task.

HR Analytics: Overcoming Challenges & Unlocking Opportunities

Is data a challenge or an asset for your HR department? Discover how to minimize the time spent on reporting while maximizing insights from your available data sources. The HR department’s monthly, weekly, and even daily reports have a wide range of complexity and importance. From the “no-fail” tasks of payroll reporting to the in-depth look at the overall health of an organization through talent acquisition and talent retention, the role of HR and the data it needs for the job are inseparable. Our analytics expert will reveal how you can: - Manage data from payroll systems - Track diversity hire information YoY - Assess the health of your organization - And more! Visit our HR Analytics page for additional resources

Detect Anomalies and Outliers with Altair Knowledge Studio

Knowledge Studio’s novelty and outlier detector node makes it easy to identify anomalies in a dataset and remove them if desired. The software supports three different methods for detecting outliers: Isolation Forest, Local Outlier Factor, and One Class SVM. This video demonstrates how to use the novelty and outlier detector. Click here to learn more about Altair Knowledge Studio.

Use Altair Knowledge Studio's XGB Node in Predictive Modeling Applications

XGB stands for “eXtreme Gradient Boosting” and is often referred to as XGBoost. Knowledge Studio includes an XGB node for predictive modeling that data scientists can use to develop solutions for classification and regression problems. Knowledge Studio’s XGB implementation supports models with several types of dependent variables and can handle single numeric DV, single binary DV, single multiclass DV, multiple numeric DVs, and multiple binary DVs. This video shows how to use Knowledge Studio’s XGB node. Click here to learn more about Altair Knowledge Studio.

AI-Supported Material Test Automation

Altair’s artificial intelligence (AI) and machine learning (ML) software helps materials scientists understand how to best fill gaps in their material databases, even when it’s impossible to test all possible variants. These advanced tools also optimize testing programs, improve efficiency, and reduce the time required to complete materials testing.

Harvesting Engineering Knowledge from Consumer Generated Data, by Mabe

In a world where everything is becoming more and more connected, Mabe, a leader in home appliances, is using product connectivity to fuel a digitization strategy that delivers consumers the best experience through their solutions and services. Learn how they are using big data, AI, and analytics to uncover insights, create new business opportunities, and inform product development. The presentation by Martin Ortega, Senior Design Engineer at Mabe, aired at Future.AI in June 2021, and is a little over 17 minutes long. Learn what it takes to build a smart product – and where to begin. Download our free eGuide. View all Future.AI 2021 Presentations

Machine Learning and Advanced Digital Gauging for Subtractive and Additive Manufacturing Processes, by Renishaw & Altair

AI-powered real-time melt-pool analytics for accelerated product development and production.

Predictive Maintenance for Heavy Equipment, by Serba Dinamik

Serba Dinamik turbines power all critical systems on oil rigs, including safety systems and pumps. The equipment must be consistently reliable with no unplanned downtime. Traditional preventative maintenance schedules are time-consuming and resource-intensive. Learn how they developed a predictive maintenance system, to take preventative action only when needed.

Leveraging SmartWorks Platform to Deploy Predictive Maintenance Strategies

The costs of unscheduled downtime in manufacturing environments can be detrimental to operations. Altair makes it easy to monitor equipment health in real-time and predict failures. See how you can gain the insights your organization needs to avoid machine failures and unplanned downtime, increase equipment utilization and production line productivity, and reduce maintenance costs.

The Power of AI and ML in Product Design

Altair products are quickly evolving into AI-driven products. Starting from the modeling and visualization products, the latest release of Altair HyperWorks includes features like shapeAI, which quickly finds and classifies parts “by shape” inside geometry files or finite element meshes - when you want to locate all of the bolts, shafts, and gears in a complex assembly - by applying machine learning.

Analyze Shapley Values with Altair® Knowledge Studio®

Knowledge Studio supports analysis of Shapley values, a solution concept from the world of cooperative game theory. Data scientists can use Shapley values to explain individual predictions of black box machine learning models, including random forest and boosting models. This video demonstrates how to use Knowledge Studio’s SHAP (Shapley Additive exPlanations) node. Click here to learn more about Altair Knowledge Studio.

Predictive Models for Connected Products

Digital technology has changed the landscape of manufacturing and product creation: Internet of Things (IoT), artificial intelligence (AI), and data analytics are connecting organizations, generating data, driving more intelligent operations, and unlocking potential like never before. New skills are needed in the world of connected products and the success of innovation will depend on companies’ digital capabilities. This is why the investments geared toward adoption of digital technologies, products, and services that allow companies to thrive in the fast-evolving economic environment is growing. This white paper outlines the steps necessary to implement machine learning predictive models for connected products using Altair Data Analytics solutions.

Build Autoregressive Integrated Moving Average (ARIMA) Machine Learning Models in Altair® Knowledge Studio®

Knowledge Studio supports Autoregressive Integrated Moving Average (ARIMA) models, a powerful way to make accurate predictions based on time series data. You can add ARIMA models to your AI workflows with a fully menu-driven user interface. The software’s Auto ARIMA functions automatically estimate values for ARIMA parameters using a grid search or step-wise algorithm. ARIMA is a simple yet powerful method for making time series forecasts, often incorporating seasonal and other types of semi-regular variations. For example, you can use ARIMA models to forecast electricity and raw materials utilization in a factory, output volumes in an oil refinery, fuel consumption for truck fleet, rail, and seaborne shipping companies, patient churn and intake volumes in hospitals, and key financial indicators for any type of business. Click here to learn more about Altair Knowledge Studio.

Altair Data Analytics for Banking, Financial Services & Insurance

Altair works with over 3,000 banks & credit unions, buy & sell-side trading organizations, security exchanges and insurance companies. Delivering best of breed applications from automated data preparation, and predictive analytics, to real-time data visualization. We provide you with technical resources from trusted subject matter experts in the field who understand your business, making your user experience seamless in transition. Altair offers a unique licensing model with cost-effective options to gain the competitive advantage in your market.

Harnessing the Power of Big Data, AI and Simulation to Accelerate Product Innovation

In a world where everything is becoming more and more connected, Mabe, a leader in home appliances, is leveraging the convergence of big data, analytics and simulation to accelerate innovation. Martin Ortega, Senior Design Engineer at Mabe, explains how they are using Altair’s AI, data analytics and simulation solutions to uncover insights, create new business opportunities, and advance product development. Learn more - click here to read how connected products deliver big ROI.

Transparent AI and Machine Learning: Altair® Knowledge Studio®

Knowledge Studio delivers explainable artificial intelligence (AI) and automates machine learning tasks to enable people to make fully informed decisions based on massive amounts of data. The software displays all the details of a model’s configuration so it is easy to understand how it generates predictions. Analysts who may not be familiar with modeling or AI processes can quickly uncover insights to help solve complicated problems. Data scientists can fine tune model parameters and develop highly sophisticated models using a drag-and-drop interface with no coding required.

Analytics for Heavy Equipment

Serba Dinamik is an engineering company specializing in operations and maintenance (O&M), engineering, procurement, construction and commissioning (EPCC), and IT solutions for energy exploration and production firms. Their team worked with Altair to develop a Smart Predictive Maintenance Data System (SPMDS) utilizing Knowledge Studio and Panopticon. Maintenance crews use Panopticon-powered dashboards built into SPMDS to monitor every sensor mounted on operating turbines in real time. AI models built with Knowledge Studio identify potential failures or issues that require engineering attention, and, based on that understanding, take turbines offline only when necessary.

Data Analytics Assessment Service

Altair’s Data Analytics Assessment Service helps answer the tough questions: • What data do I have? • Can it be leveraged for analytics? • What other data do I need and how do I get it? • What ML technology can be used with my available data? • How do I get started?

Altair Knowledge Studio™ Overview - Advanced Machine Learning and AI

Data scientists and business analysts use Altair to generate actionable insight from their data. Knowledge Studio is a market-leading easy to use machine learning and predictive analytics solution that rapidly visualizes data as it quickly generates explainable results - without requiring a single line of code. A recognized analytics leader, Knowledge Studio brings transparency and automation to machine learning with features such as AutoML and Explainable AI without restricting how models are configured and tuned, giving you control over model building.

Substitute Missing Values in Altair Knowledge Studio

Datasets often have missing values due to file corruption, failure to record data points, or other causes. Handling missing data values correctly is critical to developing accurate predictive models. Knowledge Studio makes it easy to identify datasets containing missing values and generate new substitute values based on a variety of substitution algorithms. This video walks you through a simple example of how the software’s Substitute Missing Values node works. Click here to learn more about Altair Knowledge Studio.

Data Modernization: From Gathering Dust to Gleaning Insight

As part of the Altair Data Analytics Spotlight Series, we discuss modernizing your organization's data management so that you can unlock the full value of analytics and AI. If you're interested in developing a trusted data architecture that is accessible, centralized, and strategically designed to enable scalability and smarter decision making, then this webinar is perfect for you. During this webinar, we discuss how you can: - Centralize the storage of your siloed data - Improve data integrity with data normalization platforms - Analyze all of your data for deeper predictive insights

Rapid Digital Transformation with AI-ML applied to Consumer Packaged Goods

In this webinar, we share our experience on the typical challenges faced by a CPG organization in the data analytics, AI, and ML context. A deep understanding of these challenges is also the key to the solution directions with the right mix of talent, tools, and technologies.

Detect Simpson’s Paradox with Altair® Knowledge Studio®

In simple terms, Simpson’s Paradox occurs when a trend appears in subgroups but disappears or is reversed when subgroups are combined into a single dataset. Knowledge Studio supports detection of this statistical phenomenon. In this video, you will see an example of how Simpson’s Paradox can manifest itself and how you can use Knowledge Studio to detect its presence automatically. Click here to learn more about Altair Knowledge Studio.

Working with Imbalanced Classes in Altair® Knowledge Studio®

Most machine learning algorithms assume there are equal numbers of examples for each class in the source data. Many datasets contain substantially different numbers of records for important classes — resulting in an imbalanced class problem. Failure to handle this properly results in models with poor predictive performance. Knowledge Studio has a node specifically built to handle imbalanced class issues. In this video, you will learn how to identify an imbalanced class problem and use the software’s Handle Class Imbalance node to correct it. Refer to the Imbalanced-Learn Documentation website to learn more about the challenges related to working with imbalanced classes

Using the Generalized Linear Model (GLM) Node in Altair® Knowledge Studio®

In the context of machine learning applications, GLM models allows the use of dependent variables that do not follow normal distributions. This video shows how easy it is to use Knowledge Studio’s GLM node to utilize this advanced statistical technique to build more accurate machine learning models. Click here to learn more about Altair Knowledge Studio.

Combining System Modeling & Data to Optimize Heavy Equipment Performance

Information silos present a major challenge to Heavy Equipment OEMs. Poor integration of simulation models across the product life cycle, limited reuse of models between programs, and a variation of modeling maturity across various engineering disciplines result in lack of traceability and ultimately hampers development efficiency and product performance. Using system modeling and asset-centric data analytics solutions help develop and orchestrate coherent models to increase decision-making confidence and speed.

Gain Future Insight with Your Human Resources Data

Human resources (HR) is tasked with recruiting the best talent and keeping culture at the forefront while staying on top of payroll, performance, and many other responsibilities. What if you could save time getting these tasks done while your human capital is ahead of the curve to meet your organization’s business goals?

Data-Driven Dynamic Design - How Should a Robust System Component Look?

Safety and reliability are paramount objectives of the aero-engine development work. Comprehensive dynamic simulation and testing ensure safe and reliable products. However, new design architectures with increasing demand for power density need to be developed in even shorter time scales. Robust structural dynamics are one key objective that needs to be addressed very early in the concept design. Today’s analysis tools need to make accurate dynamic predictions at the system level which takes a long time due to very large design iterations and robustness assessments. An approach to resolve this dilemma by combining Altair SimSolid with frequency-based coupling and data science thinking is presented. The presentation by Carsten Buchholz, Project Engineer for Hybrid Electric Flight Demonstrator at Rolls-Royce, aired at Future.AI in June 2021, and is almost 13 minutes long. Ready to see how your company can drive innovation with AI-powered design? Contact our solutions experts today. View all Future.AI 2021 Presentations

How to Accurately Assess Your IT Spend As a Global Technology Company

One of the challenges for CIOs and CFOs in managing IT spend is to get accurate data that can help to optimize spend. At Altair, we understand the need and we want to be your partner every step of the way. Learn how we delivered a most comprehensive data analytics solution for the IT finance team at Aptiv that helped to reduce operational time and automate the process of calculating the global IT spend accurately for managerial reporting. The presentation by Ripan Barot, Director of Professional Services and Customer Support at Altair, aired at Future.AI in June 2021, and is over 22 minutes long. See how Altair's predictive analytics solutions support calculating accurate IT spend. Contact us. View all Future.AI 2021 Presentations