As more and more corporations are moving towards cloud deployment, IBM has taken the right step to enable its integration stack to be cloud native. One such integration component is IBM App Connect Enterprise (ACE). IBM ACE is the one-stop solution to connect any application. In this Prolifics How-To Guide, we’ll learn step-by-step how to migrate IBM Integration Bus (IIB) to ACE on Kubernetes platform, specifically the AWS EKS environment.
Orlando, Fla., Feb. 27, 2024 – Prolifics, a global digital engineering leader, is proud to announce that we have received Cigna’s Silver level Healthy Workforce Designation. This recognition reflects our commitment to improving the health and well-being of our employees through our workplace wellness program.
Organizations recognized with this designation set the standard of excellence for organizational health and vitality. Prolifics’ commitment to its employees includes a monthly wellness newsletter with a range of wellbeing tips and techniques, recipes, and available support services; regularly scheduled seminars on topics ranging from “Preventing and Managing Autoimmune Disease” and “Meal Planning for Busy Families” to “Financial Wellness – Taking a Financial Selfie;” and team building events and virtual activities.
Partha Patnaik, Prolifics Head of Global Human Resources, said, “We can’t give clients our best without a healthy workforce. Our wellness programming gives our people the tools, advice and resources they need for their own physical, mental and emotional health. We’re proud of this Cigna designation as it recognizes our standard of excellence for employee health that is part of our culture.”
“Higher vitality is linked to a more motivated, connected, and productive workforce,” said Kari Knight Stevens, executive vice president and chief human resources officer, The Cigna Group. “Employers that foster vitality will fuel a healthier workplace and drive business and economic growth. That’s why we’re proud to recognize employers for their efforts to prioritize multiple dimensions of wellness, build a culture of health, and boost employee engagement.”
The Cigna Healthy Workforce Designation evaluates organizations based on the core components of their well-being program, including leadership and culture, program foundations and execution, policies and accommodations, and other areas.
Are you interested in a company committed to improving the health and well-being of its employees? Prolifics is always looking for the best and brightest. Start your career as a “Prolifian” here.
About Prolifics
At Prolifics, the work we do with our clients matters. Whether it’s literally keeping the lights on for thousands of families, improving access to medical care, helping prevent worldwide fraud or protecting the integrity and speed of supply chains, innovation and automation are significant parts of our culture. While our competitors are throwing more bodies at a project, we are applying automation to manage costs, reduce errors and deliver your results faster.
Let’s accelerate your transformation journeys throughout the digital environment – Data & AI, Integration & Applications, Business Automation, DevXOps and Test Automation. We treat our digital deliverables like a customized product – using agile practices to deliver immediate and ongoing increases in value. Visit prolifics.comto learn more.
Hyderabad, INDIA, February 21, 2024 – Prolifics, a global digital engineering leader, is proud to announce it received four awards at the 32nd edition of the World HRD Congress, held last week in Mumbai, India.
The World HRD Congress honors top initiatives in human resource practices. Prolifics’ awards are:
Dream Companies to Work for: #6 ranking
Best Employer Brand Award ‘24
Award for Excellence in Talent Management
Dream Companies to Work for, IT Sector
Satya Bolli, Prolifics Chairman & Managing Director, said, “We’re excited to have received these World HRD Congress awards. At Prolifics, we’re committed to attracting, nurturing, and retaining top talent. These accolades are a testament to our ongoing efforts to maintain Prolifics as the preferred employer in the IT industry.”
Prolifics is a perennial, highly ranked “Dream Companies to Work for” award winner. In addition to this year’s honours, Prolifics has previously won company awards for leadership development programs, workplace best practices, and individual awards for our human resources personnel.
Partha Patnaik, Prolifics Global Head of Human Resources, said, “We’re proud of this recognition – it means we’re getting great talent to come on board with us – and great talent attracts more great talent, leading to innovative work and better outcomes for our clients.”
The World HRD Congress is sponsored by human resource development and employment opportunity periodical Times Ascent. They honour organizations that produce tangible business results through innovative initiatives that promote better HR practices globally.
Prolifics is always looking for the best and brightest. Start your career as a “Prolifian” here.
About Prolifics
Prolifics is a digital engineering and IT consulting company, delivering client outcomes that matter. Innovation and automation are significant parts of our culture. While our competitors are throwing more bodies at a project, we are applying automation to manage costs, reduce errors and deliver your results faster.
Let’s accelerate your transformation journeys throughout the digital environment – Data & AI, Integration & Applications, Business Automation, DevXOps, and Test Automation. We treat our digital deliverables like a customized product – using agile practices to deliver immediate and ongoing increases in value. Visit prolifics.comto learn more.
By Ronald Zurawski, Prolifics Data Governance Strategist and Solution Architect
Reading data governance blogs related to AI, I see a lot of the same thing presented in many variations. I went to ChatGPT and asked it to write a blog for me on AI bias. You can read that ChatGPT generated blog below, italicized, then I have some thoughts on this subject.
ChatGPT generated:
Introduction:
In the realm of artificial intelligence (AI), the ethical implications of bias in models have gained prominence, demanding meticulous attention from organizations and data governance professionals alike. As data governance consultants, it is imperative to guide businesses on how to handle bias in AI models responsibly. This blog explores the pivotal role of data governance in identifying, mitigating, and preventing bias to ensure AI systems deliver fair and unbiased outcomes.
Understanding Bias in AI Models:
Bias in AI models can arise from various sources, including biased training data, algorithmic design, or even the context in which the AI system is deployed. Recognizing that bias is an inherent challenge, data governance plays a crucial role in establishing frameworks to scrutinize the entire AI lifecycle, from data collection to model deployment. A comprehensive data governance strategy should emphasize transparency, accountability, and ethical considerations, setting the foundation for fair AI practices.
Mitigating Bias through Robust Data Governance:
Data governance should prioritize proactive measures to mitigate bias in AI models. This involves implementing robust data quality controls, ensuring diverse and representative training datasets, and fostering collaboration between data scientists and domain experts to understand the potential implications of biased outcomes. Additionally, data governance frameworks must incorporate mechanisms for ongoing monitoring and evaluation, enabling organizations to detect and rectify bias as models evolve and adapt.
Implementing Ethical AI Principles:
Data governance consultants should advocate for the integration of ethical AI principles into the fabric of organizational data practices. This includes establishing clear guidelines on responsible AI use, promoting diversity in data teams, and developing comprehensive documentation to enhance transparency. By aligning data governance with ethical AI principles, organizations can not only address bias but also build trust among stakeholders and demonstrate a commitment to fairness and inclusivity.
Conclusion:
In the ever-evolving landscape of AI, data governance emerges as the linchpin for addressing bias and ensuring the responsible deployment of AI models. By fostering a culture of transparency, accountability, and ethical considerations, data governance consultants empower organizations to navigate the complexities of bias in AI, fostering a future where AI systems are not just powerful but also fair, unbiased, and aligned with the principles of responsible data governance.
Does this sound familiar? Could it be possible you read something similar before? It is a good article. Let’s look at some of the details:
“…data governance plays a crucial role in establishing frameworks…” Great! How? Let’s skip the generic consultant answer of “it depends” and think about it. If we, as data governance professionals, need to put a basic structure in place, what would that look like? What do the regulatory requirements say today? Can we reasonably expect to be included in the development process early enough to help capture, document, and possibly guide those items that need to be available when the auditor comes around? What might those items be? Let’s read the regulations coming out and see if we can provide value while walking that thin line of regulation interpretation and reduce costs/provide value to our enterprise.
“Bias in AI models can arise from various sources…” Does bias come from various sources or does bias come from our interpretation of the world around us, which we apply to this computer program’s output results? Let’s remember the AI model responds to the training data set. From a data quality point of view, we can certainly add some value to the training set considering bias. We can treat each type of training data set like any other group of critical data elements (CDEs) and start by working with the subject matter experts (SMEs) to review the profiles of the data.
“Data governance should prioritize proactive measures to mitigate bias in AI models.” Hmm, how might that work? This may be a new area to explore for data governance specialists. In the past we have always deferred to the SME to evaluate the data profiling results and followed their guidance. Is it now time for us to take a more active role and provide some push back? First, we would need to define and document the standards for what is and is not acceptable when evaluating bias. Then, apply that standard to the data set being evaluated.
I want to talk more about this topic, but, let’s think about these items first. – Ron ron.zurawski@prolifics.com
Ron is Data Governance Strategist and Solution Architect at Prolifics. His experience includes more than 10 years of working policy-driven data governance and more than 20 years in enterprise database and data warehousing systems. His industry expertise includes finance, health care and consumer product goods. Ron’s expertise is in strategic planning, systems architecture, program and project management. His tactical experience includes analytics development, architecture, ETL and database administration. Ron has experience in both Big 4 and boutique professional services organizations. Ron holds an MBA from the University of California and an MSCS from the University of
Colorado.
Our client, a leading financial institution, realized they had an overall data issue – there were more than 25 terabytes of data in 1,600 systems within the bank. The bank wasn’t sure of the data quality, or even how it was flowing within the organization.
Old legacy systems made it impossible for the bank to automate or optimize processes for even the most basic transactions. For example, if a new client walked into the bank and opened an account, the bank couldn’t onboard the client to the digital platform for an hour as it waited for a batch process to go through. This often resulted in the client leaving before the onboarding could be completed – resulting in a lost customer.
Every initiative to modernize the bank failed to deliver its promised value, because for a bank (and really most organizations) data is at the heart of delivering value, and you can’t deliver that value with data that’s not properly organized. The bank’s leadership agreed that it would not be able to compete in the world unless it dealt with its modernization challenges. They produced a solution that they believed would be a differentiating factor and give the bank a unique competitive advantage: Become the best digital bank in the industry through a transactional Master Data Management (MDM) platform for client data.
Action – An ongoing journey
The bank foresaw a multi-year journey to modernize and create a Master Client Profile (MCP) as its MDM platform – a full transactional customer master hub. They decided to go with the MDM Advanced Edition suite through IBM and needed developers to help with the development framework – the client learned that this skill is a rare expertise in the industry. IBM highly recommended Prolifics.
Phase 1: MDM architecture consulting and implementation
The bank and Prolifics recognized that the most complicated part was to build the “new world” while maintaining the old world intact. The companies knew from the beginning that the MDM transition would not be a “big bang,” but done iteratively, starting small and growing. The key was to build a transition roadmap, stay on track, sustain existing customers while enabling future customers, all while adding value and transforming the bank.
Prolifics experts started with commercial banking, which saw an immediate benefit of improving client uniqueness from 23 percent to 95 percent. Then the team transitioned various customer relationship management (CRM) platforms, including SAP. It’s important to note here that many people outside the bank/Prolifics team thought that having SAP under IBM’s MDM was impossible – but it proved to be successful.
Phase 2: Expansion and integration
Building upon the initial successes, Phase 2 focused on expanding the MDM system to include additional financial and operational systems. Prolifics integrated MDM with Salesforce to trigger workflows whenever profiles were added or updated, leveraging business process management (BPM) capabilities. The BPM workflow was customized for the data owners and allowed for information flow to other departments for their specific tasks. This phase also involved enhancements to ensure seamless integration with the bank’s core banking system for retail customers and synchronization with the bank’s Common Reporting Standard (CRS) system user interface (UI) and database. Prolifics developed nine additional services to retrieve retail customer data from MDM and facilitate further integration with SAP.
Ongoing: Managed services and continuous improvement
After the successful phase completions, our client has transitioned to a managed services model. Prolifics continues to support the bank by augmenting the teams responsible for maintaining the MDM solution. This model ensures ongoing support, facilitates the implementation of enhancements, and accommodates the addition of new data sources to the MDM ecosystem.
Result – A foundation for a digital bank you can’t do without
There are several examples of how the bank is utilizing the MDM foundation created with Prolifics help (see below). However, in the bigger picture, the MDM will be “the gift that keeps on giving.” With robust customer data in one place, there’s an endless amount of flexibility and possibility, which the different lines of business will take advantage of as the MDM becomes increasingly connected. So, the biggest benefit is that the bank personnel will now have the same information on all the platforms that have been connected to the MDM. In terms of process efficiency and trusting the data, this is a huge advantage. The bank has realized many benefits, including:
Consistency and access – In the bank’s private banking service, they previously had to create the profile of a prospective client in one system through the onboarding, then go to another system to create company data and do compliance. Now, the profile is created in one place, and it’s already present for other uses and needs. The bank’s personnel don’t have to re-key the information or create duplicates.
Efficiency – Over time, the bank generated up to 7,000 duplicates for companies. That’s been resolved through connection with the new MDM platform.
Trusted data – The bank has managed to eliminate almost 100 percent of free text within the data model. With concentrated, structured data and centralized rules, building algorithms and using artificial intelligence (AI) will provide valuable insights.
Technology – IBM MDM Advanced Edition
IBM MDM Advanced Edition enables multiple MDM styles and domains to work together to provide a comprehensive set of capabilities to meet the demanding MDM requirements. Built-in tools help streamline the planning and addition of physical capabilities:
Features highly accurate probabilistic matching and search
Supports multiple implementation styles
Includes comprehensive pre-built and extensible data models and business services
Supports large transaction loads and high-availability environments
Helps improve data quality by implementing policies and processes to coordinate multistep and multi-role workflow for data governance
Features a comprehensive security model to help you manage access and actions
About Prolifics
At Prolifics, the work we do with our clients matters. Whether it’s literally keeping the lights on for thousands of families, improving access to medical care, helping prevent worldwide fraud or protecting the integrity and speed of supply chains, innovation and automation are significant parts of our culture. While our competitors throw more bodies at a project, we apply automation to manage costs, reduce errors and deliver your results faster. We accelerate your journey throughout the digital environment – Data & AI, Integration & Applications, Business Automation, DevXOps, and Test Automation. We treat our digital deliverables like a customized product, with agile practices to deliver immediate, ongoing increases in value.
By Chris Isayan, Prolifics Associate VP, Digital Experience
Introduction
As I write this blog, I want to acknowledge the value of the AS/400 system and programs written in RPG. AS/400 RPG programs are still at the foundation of many businesses and there are still many mission-critical applications running in AS/400 RPG that have proven their reliability; some can’t even recall the last time they needed a restart. They are also highly secure—rarely you hear of an AS/400 being breached. These are just a couple of examples.
If these applications are so stable, secure, etc., then why modernize? The primary reason I hear from our clients is that the AS/400 RPG skill deficit and a shrinking talent pool. The secondary reasons, which are less emphasized, include the cost of making changes due to the monolithic nature of the application. Also, it is harder to use modern application development tools with RPG. We had another customer say, it takes too long to train new end-users on the 5250 “green screens,” and it lacks the capabilities today’s users expect. In short, while we recommend modernizing, the motivations and decision when to modernize ultimately rests with each organization, depending on their unique situation.
Concerns
Most clients who decided to modernize have reservations. The primary concern we hear from our clients is the years of complex rules and workflows embedded in RPG programs, coupled with a lack of clear separation between screen code and code behind. Clients think there is a good chance of losing essential logic during modernization. Additionally, the AS/400 database model is hierarchical in nature, organized in a tree-like structure, which makes it harder to understand for traditional RDMS experts.
Therefore, as you modernize the front-end, a deep understanding of the hierarchical model becomes crucial. Plus, transitioning to a relational database model, managing data migration, refactoring all dependent reporting and backend processes pose additional challenges. However, for now, let’s stay focused on the front-end.
Modernization Approach
Generally, we start with a workshop, assessment, and discovery phase. The fact is that a lot of applications on AS/400 are customized around the operations of a particular business with a “bunch of one-off” odd scenarios unique to each business. This can complicate matters when trying to plug something off-the-shelf.
So, as a guide, we identify client’s pain points, business nuances and operational flows, business capabilities clients have, or new capabilities they’ll need. We then rationalize their systems to understand what stays, what gets re-written and what gets off-the-shelf replacement. We might recommend that AS/400 hardware stay and host the applications that are written in the new programming language. For now, fast-forward and assume we have a prioritized list, budget, etc. to start the development cycle where we are writing BRDs, reverse engineering code to functional requirements, coding, functional testing, and handing over user acceptance testing. Is all of this done manually? What tools are available to help with automation? The good news is that there are reputable companies stating that they have tools that convert AS/400 frontend code. However, the bad news is that they won’t license the tools, i.e., they are for “internal use” only.
Recently, we’ve been exploring the development of our own tools using GenAI. Despite the complexity of AS/400 app modernization, we were able to utilize GenAI to deconstruct the process into three key steps: understanding the code, reverse engineering the business capabilities, and code translation to modern language. This streamlined approach accelerated the process and improved the quality of the outcome.
So, let’s look at what Gen AI can do. Our objective is in multiple folds, (1) ability to point to entire code, (2) extract business rules and request to generate code explanation for overall or specific business capability (3) ability to translate the code for specific business capability to another language. In a more practical sense, (1) point to supply chain ERP code, (2) request to describe the procurement code and (3) generate code for “New Purchase Order” screen; Angular for front-end and node.js for middle tier without impacting the database. Assuming you have two-week sprints, you start the app dev cycle. This model best fits when the application architect already created the scaffold code that includes essential structures, architectural decisions, design patterns and best practices. This involves breaking down the application in multiple app.modules, implementing router guards, state management, logging, authentication and authorization, off-line capabilities, etc. Once the foundation structure is established, the Gen AI generated code can be integrated into the scaffold.
Note: you can feed the scaffold code Gen AI to fine-tune the model and regenerate the “New Purchase Order” screen. This approach achieves a balance between manual control over the architecture and the automated generation of specific code components. We can also specify the use of common libraries, such as Angular Material and code that will be generated using Angular Materials.
One issue we found was when using a large language model like ChatGPT, which has a cutoff date for its training data, there’s a risk that the code it provides may be outdated and may include deprecated methods and libraries, especially in fast-evolving programming frameworks like Angular, React, and others. So, we overcame this issue by provisioning our own LLM on the cloud and, through prompt engineering and fine-tuning, were able to bring the model to our liking. Also, you may need to alternate between models (such as code-daVinci, text-daVinci, and GPT) depending on whether you are generating code explanation or code translation. Additionally, we engineered the model to adhere to best practices, design patterns, and specific architectures to produce the expected code. But even with all the prompt-engineering and fine-tuning, it’s essential to manually review the code, run automated unit tests, and assert potential issues, and finally, fine-tune the model further.
Another issue we encountered was the inconsistency of the generated code. In other words, each time you request to generate code, you’ll receive a slightly different translation of the same RPG code. While you can adjust parameters like temperature, provide templates to achieve consistent behavior, it is essential that the code is manually reviewed. We are still working on implementing a set of rules and templates to ensure more consistency in generated code. In summary, while we strongly recommend using Gen AI for code explanation, achieving accurate and consistent code translation requires more prompt-engineering and templating.
It is noteworthy to mention that IBM watsonx Code Assistant for Z solution uses both rules-based and Gen AI process for code translation. Additionally, it takes into account programs on the mainframe and maps out architectural flow diagrams for each, with all of their data inputs and outputs. Unfortunately, this only works on Mainframe Cobol code on Z.
Coexistence of Legacy and Modern Applications
As you migrate from AS/400 RPGLE and DDS code to a more modern code, the entire ERP modernization process may occur in phases, taking months and years. For instance, you might release the procurement part of the application first, followed by inventory and warehouse management, transportation, etc. As you roll out different parts of the legacy ERP system, both legacy and modern applications will coexist. It’s crucial to have a solid rollout plan, legacy decommission plan, etc. Additionally, keep in mind that while the applications are running side by side, you need to have a well-thought-out plan to minimize maintenance costs, such as optimizing or re-utilizing hardware and other resources for both systems. Lastly, ensure you have a plan in place to train staff who are accustomed to maintaining the legacy app so they can effectively maintain the modern app. These considerations need to be planned upfront and not treated as an afterthought.
Deployment & Change Management:
From the business user’s perspective, Deployment & Change Management plays a pivotal role in ensuring a seamless transition to modern applications. It’s important to note that many experienced end users love their “green screens.” In fact, some don’t even look at the screen; they predominantly use the keyboard (not the mouse) to navigate, a couple of tab presses, couple of function key presses and they are done. Therefore, it is critical not to compromise functionality during modernization and to have a good understanding of the system usage from an end-user perspective. Also, business capabilities need to be delivered in their entirety. For example, plan the deployment phases considering the specific workflows of business users to minimize users going back and forth between legacy and modern applications. If necessary, provide single sign-on capabilities to ensure seamless navigation for the end-users.
Effective change management is essential to address concerns, keep a log of these concerns, create “Run Books,” communicate changes transparently, and provide adequate training for a smooth adoption of the modern application. Utilize pilot users as your champions to foster a positive environment, enabling remaining users to efficiently leverage the advancements brought about by the modern app. Ideally, the goal is to experience zero disruptions to daily operations and become more efficient in what they do.
Conclusion
More and more companies are gradually transitioning their AS/400 RPG code to modern programming languages, and each company needs to decide when to transition. Our recommendation is transition while you have in-house RPG experts to provide an oversight and facilitate a smooth transitioning. We believe that your experienced internal RPG teams are essential for an effective transition and success of this modernization effort. The best solution is to partner with digital engineering companies, like Prolifics, that have an outstanding track record of delivering modern applications, as well as having a good, automated approach in reverse engineering applications.
Prolifics also provides prototypes, accelerators such as fine-tuned Gen AI models, which can reverse engineer the application, create data models and starter code. Additionally, Prolifics offers automation testing tools to accelerate the modernization journey with the highest quality. The Prolifics team will integrate with your existing teams and will work with you on a customized approach, as well as estimating cost and timelines for modernizing your application. With a teams integrated approach, your internal teams will understand the new application architecture, will be trained, and can easily take ownership at the project’s conclusion.
Special Thanks
I would like to express my sincere appreciation to Prolifics’ Konrad Konarski, Gregory Hodgkinson, Honda Bhyat, Rajeev Sharma, Ramnath Nalluri and Sheryl Oleksa for their valuable feedback and insights during the development of this blog. Their thoughtful input significantly enhanced the quality and depth of the content. Thank you for your valuable contributions.
Chris Isayan, Prolifics Associate VP, Digital Experience, has extensive experience in assessing, designing and delivering at a global level. Chris is known to “learn the industry first,” then works with the line of business to infuse technology into every stage of business processes, empowering every organization, business unit and individual to do more with less. Presently, Chris is focused on utilizing Cloud and AI/ML to accelerate digital transformation. Chris prototypes his designs so they are not just ideas, whether it is using Cloud services, out-of-box computer vision and/or natural language processing (NLP) or creating his own models.
Navigating the complexities of Electronic Data Interchange (EDI) supporting the healthcare industry can be challenging. Challenges with custom business rules, integration of technologies, and ensuring compliance add to the burden. However, Andrea (Andi) Minarcin, Director of Healthcare Business Development at Prolifics, says there’s relief. We asked Andi how she helps clients navigate complexities and drive transformative change on their EDI platform. Here’s what she said!
Q&A with Andi Minarcin
What challenges are healthcare payers facing, and what are their objectives?
I work with healthcare payers, like this leading health insurance provider, who are committed to improving the way they manage EDI, aiming to make operations smoother, reduce costs, and improve member and provider experience.
Many of my clients feel “trapped” in their current EDI system. They’re looking at new ways to improve transaction ingestion and increase transaction ingestion, transparency and traceability, seamlessly connect new systems with existing technologies, save money without sacrificing quality, and tailor reports and dashboards to fit their business needs all while staying compliant.
How can we process more faster and with fewer mistakes?
It’s tough to track every transaction file, ensuring each one is processed on time. My clients require more visibility into the life of each file. Yet, due to the increased complexity associated with business and compliance rules, high volume of transactions, and number of “hops” in the life of each EDI file, many solutions lack real-time status. This leads to delays or failures in member enrollment, claims adjudication, electronic payment, etc.
From limited insight to 100% visibility
Our (Prolifics) EDI Modernization for Healthcare (EM4H) solution addresses these limitations and enables timely and accurate processing. We give you personalized access to your business transaction data, including easily customizable reports and dashboards – any way you need it. The transactions are not just processed; they are tracked, traced, stored and audited with precision in high-volume environments.
How can collaboration among multiple systems and parties be improved?
Flexibility and adaptability are key focuses for healthcare payers in a rapidly changing market. However, many struggle with rigid systems that are difficult to modify or integrate with newer technologies.
From cluttered connections to clear integration
Prolifics opens the door to complete integration capabilities. No more hidden schemas or databases. Due to the use of off-the-shelf software EM4H directly integrates with virtually any current and future business system, preserving critical IT investments. Businesses can enjoy a more streamlined approach to connectivity, eliminating unnecessary hurdles and paving the way for efficient operations.
Additionally, healthcare payers can smoothly exchange data between different systems and partners. It doesn’t matter if their environment is on prem, in the cloud, or both – we make sure everything flows smoothly, making the transactions process a whole lot easier.
How can we reduce operational costs?
Healthcare payers know that maintaining and updating legacy EDI systems can be quite an expensive headache year over year. Budgets take a hit every time changes are made.
From budget headaches to manageable costs
Prolifics offers a cost-effective alternative with transparent pricing, allowing organizations to modernize their EDI platform without breaking the bank. Once deployed, the solution is theirs without the need to be locked into an expensive multi-year contract.
I tell my clients to say “goodbye” to exorbitant pricing schemes. No “per-anything” fees—just transparent pricing that aligns with their budgets.
How to prepare for the future?
Here’s my advice: Start by taking a hard look at your current EDI platform. Are you feeling trapped in a rigid, costly system? Are transactions processed accurately and promptly without errors? Are you stuck paying for updates you don’t really need? Does the size, time and cost of an upgrade require a large project team? If so, it’s time to explore alternatives like Prolifics EM4H.
Final thoughts?
Addressing the EDI challenges in healthcare is no small feat. It’s critical to have the right expertise and thinking outside the box. Prolifics is leading the charge with innovative solutions. Quick fixes are just that, quick and short-lived. Revolutionizing the way healthcare payers operate is necessary for longevity in the healthcare industry. By optimizing systems and fostering collaboration, Prolifics is helping them manage costs more effectively. And the best part? It’s not just about the numbers—it’s about improving outcomes for patients and providers alike, something that truly drives us forward.
Visit our website or click below to download our EDI Modernization for Healthcare white paper.
By Ronald Zurawski, Prolifics Data Governance Strategist and Solution Architect
One of the new terms spreading into Data Governance vernacular is “Drift.” How do we, as Data Governance Specialists, begin to adjust our Data Governance programs to begin to accommodate drift and the possible regulatory and compliance issues that we may face?
First, let’s take a look at what “Drift” is. Let’s say the developers have put together an AI data model and have trained it to do a specific task. As time passes, new input may need to be added for the model to evaluate. For example, in the Health Insurance industry, claims are evaluated against IDC-10 codes. These codes have been known to change over time. If developers simply add the new codes to the training set and place the model back into learning mode, how will the future output of the model change? It will change. This change is called drift. The business will need to evaluate if this drift is good or bad for the intended purpose.
From a Data Governance perspective, we might profile the output data from the AI Model and then work with the SMEs (subject matter experts) and data owners to determine if the results are acceptable. Going back to our Health Insurance industry example, some of the IDC-10 codes may be added. Some may be deprecated. We know that smaller providers may not update their system immediately, yet some claims may need to be forwarded to entities for reimbursement, like the government.
How do we as Data Governance specialists interact with these AI Models? Do we mandate that AI Model Code and Data Training Sets be secured and archived before the model is placed into production? Will this become a regulatory requirement? Do we laboriously go through multiple iterations of large output results from the AI Model and confirm Drift has not caused the model to stray from its initial accuracy or purpose?
In the past our software, OS and any underlying components of the infrastructure have been built to always produce the same result. We were assured that an If-Then statement would return the same result every time and could build test systems that confirmed this. Now we are working with interactions between numerical numbers. If we were to change the order the underlying AI Model evaluates its neural network, can we guarantee the same results?
AI Drift is opening up a whole new set of challenges for Data Governance. We will need to take those lessons learned from Glossary builds, Data Quality assessments and Data Lineage pulls, applying them to the whole new world of AI. This is going to be fun!
Ron is Data Governance Strategist and Solution Architect at Prolifics. His experience includes more than 10 years of working policy-driven data governance and more than 20 years in enterprise database and data warehousing systems. His industry expertise includes finance, health care and consumer product goods. Ron’s expertise is in strategic planning, systems architecture, program and project management. His tactical experience includes analytics development, architecture, ETL and database administration. Ron has experience in both Big 4 and boutique professional services organizations. Ron holds an MBA from the University of California and an MSCS from the University of
Colorado.
Chris Isayan, Prolifics Associate VP, Digital Experience
