Kalypso Expands Digital Expertise with Rockwell Automation's Acquisition of Knowledge Lens | Read more

Turn PLM data into insights that improve results with Machine Learning

Background image: Data Science PLI 2023 Kalypso

Businesses are sitting on months, even years, of untapped product data, and they are not capitalizing on the value of today’s product lifecycle management (PLM) capabilities. This is where product lifecycle intelligence (PLI) comes into play.

PLI is an evolution of PLM, focused on mining insights from product development data that has accumulated within PLM environments and other integrated business systems. Powered by advanced analytics and machine learning techniques, PLI helps organizations identify patterns, form predictions and prescribe improvements to product development metrics like data quality, right first-time rates, time to market, regulatory compliance, performance and manufacturability.

Real Results

  • 70-90% accuracy in design failure prediction
  • 20% reduction in rework and approval time
  • 8-10% part error detection rate
  • 2-3 months time to market reduction
  • 53% reduction in classification time

PLI in Action: A Structured, Data-Driven Approach to Solving Problems

Kalypso’s approach to PLI is powered by a set of proven use cases and methodologies with solutions tailored to meet client needs. The use cases below are just a few of the ways PLI is helping innovators solve key challenges and unlock insights across the product lifecycle.

PLI + PLM

PLM data is available, plentiful and structured, making PLM a logical starting point for many companies, with clear benefits in R&D and new product development.

Data Quality

Enrich PLM data quality - identify duplicates, incomplete, anomalous and erroneous data.

Classification

Organize and define part libraries, predict classification and identify parts for reuse.

Image & Text Analysis

Digitize data within PDF; perform image recognition and comparison.

Rework & Rejection

Predict riskiness of rejection. Identify errors which may result in rework.

Product Design Optimization

Prescribe improved design alternatives to meet innovation objectives.

PLI + Enterprise Systems

For companies with structured data in other enterprise systems, PLI can provide value to additional teams, including manufacturing, supply chain and service.

Product Performance (with IoT)

Bring performance insights from connected products back into the R&D process. Facilitate data-driven design.

Product Quality (with QMS)

Correlate design decisions to product quality results. Predict and avoid quality issues.

Manufacturing Performance (with MES)

Correlate design decisions to manufacturing performance (scrap, yield, quality).

Cost (with ERP)

Leverage cost and procurement data to identify cost reduction opportunities.

Customer Experience (with CRM)

Correlated design decisions to customer experience, adverse events and complaints.

How We Help Companies Deliver Analytics at Scale with PLI

Identify High Impact Use Cases

We come equipped with a library of proven use cases but work with you to identify the opportunities connected to your business objectives. Use cases with the highest potential impact and value are prioritized first.

Create a “Value First” MVP

Initial development efforts are centered on a narrow use case focus but executed with depth of value creation. We drive towards quick time to value with 8-12 weeks for an initial MVP.

Operationalize and Integrate the Solution into the Work Process

PLI solutions are deployed as digital "advisors" to augment, not replace, human decision power. Solutions are architected so that the analytics engine operates in a stand-alone environment, with the outputs integrated directly into the PLM user interface.

Build the Sustaining Organization to Continuously Deliver Value

Agile processes are established to continuously and quickly scale capabilities (new value creation every 6-8 weeks). We help you establish the delivery organization, equipped with Analytics Translators operating as the "tip of the spear" to translate business opportunities into analytics solutions. This is backed by a value realization strategy for each PLI solution to ensure results are being measured and realized.

Featured Case Studies & Demos

Deployed via a suite of user-centric apps, PLI addresses core business needs of PLM users, including data migration, new product development cycle times, change management, product quality, supplier management, manufacturability and regulatory compliance.

Use Case Demo: PLI for Engineering Change Management

In the following use case demo, we’re a discrete manufacturer making complex products using a PLM application to manage product data.

The engineering change management process is a critical component to managing product improvements and changes to products that are in market. The implementation of these changes is highly variable and one of the biggest contributors to the overall cycle time of a change.

PLI takes the variability and guess work out of the implementation timeline by using the rich dataset that the PLM system has collected. A change manager can now receive real-time feedback on implementation tasks and overall implementation time while simply building the plan.

Background image: 1
Case Study / $10B+ Food & Beverage Company

Case Study / $10B+ Food & Beverage Company: Resolving Data Inconsistencies with Data Science

  • Identified over 5,000 data misalignments between three systems and five data environments

  • Synchronized data across the various systems and environments, creating a consistent dataset across systems

  • Saved hundreds of manual labor hours on the initial data clean up, and continued hours will be saved using the new system for ongoing maintenance

Data Synchronization with Data Science

Client had data across three different internal data sources, and it was not in sync, causing discrepancies between how product data was defined in different systems. The goal was to decrease manual data input labor and data errors across the three sources and five environments. It was recognized that data science would be necessary to synchronize the data and leverage it as source of truth moving forward, internally and externally with suppliers. The custom code created identified misalignments and produced a recommended change based on client's global data standards. The recommended changes were reviewed by SMEs and once approved, scheduled within the systems' existing IT refresh schedules to ensure this program would have long lasting results. Our approach ensured consistent data resolution and minimized SME time needed.

Background image: Returns analysis case study
Case Study / Multi $B Home Improvement Retailer

Case Study / Multi $B Home Improvement Retailer: Automated Returns Analysis for a Multi $B Home Improvement Retailer

  • 97% returns classification accuracy

  • Increased complaint processing speed by 100x

  • Identified critical product quality and safety concerns

  • Improved future product designs with insights from return data

Automated Returns Analysis for a Multi $B Home Improvement Retailer

Client had enormous volumes of product returns data to manually categorize and interpret. This was a slow process that negatively impacted customer satisfaction and led to a lack of visibility to product development and quality control functions.

Our approach included first collecting a large dataset of returns and manually labeling a subset with the correct return classifications. Then, we applied natural language processing and supervised learning techniques to process and categorize the unstructured return descriptions into structured return categories. With a system in place to automatically classify consumer responses, the client had a data-empowered team. They could more quickly identify return trends, pull problematic or low-quality product from shelf and easily close the “learning loop” by sharing the insights with product development and marketing teams to make necessary changes.

The output of this model could then be redeployed in a predictive model to proactively identify buying trends and return trends. Teams gained insight into unfavorable, high-risk and low-quality product or categories of products and could pave a path for fewer returns and happier customers.

Thought Leaders

Jordan Reynolds 2018
Principal & Global Practice Leader, Data Science & AI