Case Studies

Filter by Topic

Elder Research developed an automated data pipeline to cleanse data from millions of documents and feed a data visualization tool used to explore and identify risky network relationships. The solution enabled the client to automate significant portions of work saving time and cost, make data-driven decisions, prioritize investigative resources, and gain new business value from the data.
Elder Research implemented an automated framework for time-series forecasting at a major logistics company. Our system, combining R and Apache Spark, produces 35 million forecasts in under one hour, and selects the optimal time-series forecast algorithm in each of three forecasting windows. Forecast results from our framework were 88% accurate at a four-week horizon.
Elder Research designed and deployed tools for high-end text mining to search, index, and automatically classify information related to animal infectious diseases. The solution enabled analysts to validate incidents of animal disease and make recommendations for dealing with them at the earliest stage possible.
Department of Labor Office of Inspector General (DOL-OIG) contracted with Elder Research to create a predictive model to detect fraud in Office of Workers’ Compensation Program (OWCP) data. The goals of this project were to highlight abnormalities in the claims data that could be used to form the basis of future audits and to create visualization tools to enable auditors to explore model results. The RADR tool amplifies the productivity of DOLOIG auditors and reduced case investigation time from days to hours, combining client goals and expertise with objective measures of risk
Elder Research developed an advanced analytics prototype to detect potential fraud, waste, and abuse by Medicare and Medicaid dental insurance service providers. The analytics solution increased fraud detection by a factor of ten and enabled the client to more efficiently target suspect claims for investigation.
After investing heavily to investigate a new potential drug, the compound was not passing the statistical tests required by the FDA. Pharmacia & Upjohn invited Elder Research to examine the data and determine the drug’s viability. The research discovered a real effect, and these decisive results were communicated to decision makers using a novel visualization technique.
Elder Research combined state-of-the-art text mining algorithms with traditional statistical techniques to create a solution for the Social Security Administration to rank disability claims for approval. The results were more accurate and more consistent than any single doctor’s decision and allowed 20% of the claims to be approved immediately.
Elder Research examined a dozen major data mining techniques to evaluate their performance and gain insight on which credit card accounts were likely to default compared to the client’s world-class baseline model. The resulting model ensemble significantly improved early identification of bad credit risks.
By applying advanced techniques for modeling and visualizing customer records, Elder Research created a combined data and text mining solution to increase mar- keting efficiency and reduce churn. The model improved targeted messages which resulted in higher profitability for nTelos, a regional mobile phone carrier.
DentaQuest engaged Elder Research to improve on existing models used for assessing the performance of Medicaid Dental providers. The goal was to create a single simplified risk score that would provide a holistic 360 degree view for each service provider. We developed a provider risk scoring model that enabled targeted intervention with low quality providers and reduced per patient cost by nearly 20 percent.
Elder Research designed and deployed an automated fraud detection solution for the New York Department of Labor Unemployment Insurance Integrity Center of Excellence. The tool was estimated to have identified 1200 claims annually before the current investigative process with annual projected savings of $972,000 in recoverable and nearly $392,000 in non-recoverable overpayments.
Elder Research designed and deployed an automated fraud detection and visualization solution for a national Workers’ Compensation Insurance Program to improve the efficiency of fraud detection and investigation by prioritizing high-risk cases.. Investigations and forensic analysis that took hours can now be completed in minutes, making the most efficient use of limited and valuable resources.
Elder Research identified a molecular signature for asthma and developed a predictive algorithm to define asthma, and identify asthma sufferers who are ill and at risk for major respiratory complications, allowing for intervention prior to onset of acute asthma symptoms, thereby potentially preventing hospital stays and even loss of life.
Elder Research developed a data-driven risk assessment framework to triage Worker’s Compensation claims, prioritizing high risk cases for review and fast-tracking other cases to avoid manual review and adjudication. Claims that are routed to the fast track are assigned risk-based maximum payment limits for intelligent ongoing claims management.
Elder Research developed predictive models for the Michael J. Fox Foundation to score and rank medical tests and biomarkers to find those that offer the greatest value in predicting Parkinson’s disease. Deployed in a clinic, the Elder Research solution will help clinicians diagnose Parkinson’s based on available tests, and recommend the fewest additional (or next best) tests to improve disease prediction.
Elder Research partnered with a diversified bank to predict account closures, prioritize marketing interventions, and understand precursors to customer churn. We built a model that was 20% more effective at predicting customer churn than existing techniques.
Elder Research developed a predictive model to score and rank patients for outreach by development officers, based on their likelihood to begin a philanthropic relationship with the health foundation. The model identified 20-30% more patients with a high likelihood of becoming a grateful donor.
Elder Research created a risk model to help the U.S.Postal Service Office of Inspector General prioritize review of facility leases that were due for renewal. The risk model enabled business analysts renegotiating lease rates to focus on facilities with the most risk or highest financial impact. Projected savings was $99 million over 5 years.
Elder Research developed a risk scoring model to optimize the management of long-term care claims. The regression model successfully predicted which claims would experience expanded payout over time, identifying claims most in need of clinical review. The proactive recommendations for patient service resulted in better patient care and more efficient claims management.
Elder Research partnered with the U.S. Postal Service Office of Inspector General to develop and deploy a custom solution to identify and prioritize questionable contracts and healthcare claims for investigation. Leads generated were 74% actionable, resulting in over $11 million in recoveries, restitutions, and cost avoidance in the first year.
Elder Research designed, prototyped, piloted, and deployed an automated service provider and warranty fraud detection system. The solution prioritized investigative workload to maximize resource utilization and minimize loss to fraud and is credited with saving over $67 million in service provider and warranty fraud.
Peregrine Systems advanced to the forefront of the IT management industry by partnering with Elder Research data mining and software development experts to develop its DecisionCenter software. IT executives can now accurately predetermine how changes made to staff and infrastructure resources will affect business.
Elder Research text mined survey data and provided exploratory and predictive analysis to identify insights and trends that affected conference attendance. This helped guide the client’s conference content programming and global conference planning.
Elder Research largely automated the extraction of valuable underwriting information from scanned Attending Physician Statement documents using text mining tools and techniques. Extracted text features were transformed into electronic formats suitable for predictive modeling.
Elder Research applied state-of-the-art text mining techniques to the problem of sentiment analysis. The solution focused on the entire survey text rather than limiting analysis to lists of positive and negative keywords. This approach more accurately identified important issues and ignored off-topic comments, leading to more focused action and improved customer loyalty.
Elder Research created an automated evaluation of the impact a printer supplies loyalty program had on customer lifetime value, retention, and market share. The solution increased program enrollment by 35%, resulting in more than $600 million in sales over five years.
Elder Research developed a user segmentation model based on SolidWorks’ software usage logs. These segments, reproducible with 92% accuracy, served as the basis for helping SolidWorks employ product log analytics to better understand, communicate with, and serve their users.
Elder Research used sensor data to develop risk models that predicted well freezes with 70% accuracy, enabling targeted well intervention to reduce freeze remediation cost and recover gas production that would have been lost or deferred.
Elder Research validated the processes and methodologies applied by RightShip in the development of RightShip Qi, a new model that enhances maritime safety by predicting the casualty risk of ships. With the new RightShip Qi model, the organization seeks to take ship vetting to an entirely new level by implementing a data-driven solution with machine learning techniques.