Saferock

Improve Your Mission with our analytics

We Support your Mission with our advanced analytics

We support your mission and improve productivity through modeling, forecasting, and simulations. We enable your policy decisions with our proven digital modernization strategies and data-driven decision support tools. Here is our Capability Statement.

BENEFITS Our agile solutions can: – Identify anomalies and errors using AI, ML, and RPA  – Strengthen models, forecasts, and simulations – Accurately and quickly flag fraud and waste – Improve teamwork and focus on what matters most – Reduce workload for staff and increase productivity

ANOMALY DETECTION: CASE STUDIES

SafeRock has broad experience in anomaly detection across multiple sectors. We can process millions of records and manage billions of data points to create automated management systems that help our clients identify outliers, anomalies, and areas of risk and potential threat.

  • Reduce Fraud and Waste

    SafeRock Reduces Fraud and Waste   Situation
    • A vendor fund management department wanted to eliminate errors, duplicate entries, waste, and potential fraud. Management also wanted to identify emerging partners that over-performed their targets, in order to develop them as Key Strategic Partners.  
    Approach
    • We created a unified system for 3 years of live transactions, representing 85,000+ items and vendor financial commitments for $300+ million. Our system identified anomalies as soon as data was received for 12,000 items daily, and separately grouped outlier values into items for a) supervised correction and approval, b) discarding, and c) additional research. 
    Result
    • Our system successfully detected and sorted anomalies and outliers. This increased staff productivity, eliminated duplicate record keeping, and reduced staff burden. 
    • Increased annual vendor fund capture by 12% and staff time savings valued at $2.4 million.

    Technical Resources

    • DevOps, MLOps, AI, RPA, Vendor Fund SMEs, SQL, batch processing, SafeRock’s TOROS solution, relational database engine.

  • Create Enterprise Data Lake

    NetVantage Delivers Enterprise Data Lake    Situation
    • A client with 20+ billion data points to analyze asked for a unified Enterprise Data Lake, using AI, ML and RPA to automatically eliminate errors at the point of data entry.
    • The Data Lake improved data governance, enhanced functionality and systematically measured Key Performance Indicators, which increased departmental productivity and results.
    Approach
    • We established a clean data lake with strong governance, high data security, and rigorous data hygiene to keep information consistently clean.
    • Our cloud-based system de-duped records for 100,000+ items daily across a 100k x 100k matrix (10 billion cells). This simultaneously delivered clean master data management and calculated key performance indicators. 
    Result
    • The client reduced costs by 12.4% annually and increased sales by 19.6% per year. This program simultaneously improved top line sales and bottom line results for the company. 

    Technical Resources

    • DevSecOps, MLOps, AI/ML, RPA, Agile process, AWS using a relational database engine, SQL stored procedures, SAP, Oracle, SafeRock’s NetVantage solution, user-centered design, batch and BI reporting.

  • Detect Anomalies and Outliers

    Innovative Techniques Accurately Detect Anomalies   Situation
    • Estimating oil and gas reserves is a tricky – and important – matter for energy companies. The quantity of reserves directly correlates to the company’s market value, and accurate production forecasts relate to its stock market price. Estimated ultimate reserves (EUR) are mathematically calculated from each well’s historical production curve and anticipated future production. The project called on us to dynamically calculate EUR and improve the accuracy of oil and gas production for over 100,000 wells in key shale fields such as Eagle Ford, Haynesville, and Permian. This system improved the production forecasts for E&P operators while simultaneously identifying errors, new discoveries, as well as fading wells.
    Approach
    • We delivered an automated system which combined anomaly detection and well productivity decline curves, improved EUR estimates, and generated type curves for each geographic region. Our system aimed to increase the accuracy of new well EURs (which impacts company value) and simultaneously improve the accuracy of quarterly production forecasts (which impacts stock market price).
    Result

    • Our system greatly improved the accuracy in 1, 2, and 6 month forecasts. Our estimates were more accurate than the predictions of Wall Street experts for 74% of the wells.

    Technical Resources

    • DevSecOps, MLOps, AI/ML, supervised reporting, Statistics SMEs, Shale and Geology SMEs, Agile process, AWS with relational database, SafeRock’s TOROS solution, Python, R and Shiny.

MODELING AND FORECASTING: CASE STUDIES

SafeRock’s robust mathematical modeling creates accurate, best-in-class forecasts for our clients. We have experience in predictive analytics across several sectors ranging from retail to E&P. Our successful track record is codified in sophisticated, reusable algorithms, models, and cloud-based solutions. 

  • Forecast COVID-19

    Accurately Forecasted COVID-19 Spread    Situation
    • A client requested an econometric analysis of COVID-19 correlates, as a way to improve their national business re-opening strategy as the work environment changes and recovers from the Pandemic.
    Approach
    • We analyzed variables associated with COVID-19 spread, including social vulnerability, income, wealth, education, and health, and integrated them into a robust predictive model. We used data for 3,100 counties covering 90%+ of the United States population, to achieve highly accurate, county-level forecasts for all counties in the United States.
    Result

    • Our models were accurate in forecasting COVID-19 incidence with 98% accuracy. The predictive factors were highly significant at the 99% level.

    Technical Resources

    • DevOps, MLOps, supervised analysis and reporting, Statistics SMEs, SAS, Agile team, AWS, Python, R and Shiny.

  • Optimize Supply Chain

    Effectively Optimized Supply Chain for North America   Situation
    • A national brand sought to optimize their supply chain through using predictive analytics. They wanted to reduce the incident rate of items being out-of-stock or overstocked, and ensure that there was adequate supply at each of the 1,200+ store locations for the company.
    Approach
    • Tapping into pricing, inventory, and store databases, we modeled sales demand and last-minute pricing, related this to in-stock quantities, and proactively identified potential bottlenecks.
    Result
    • The cloud-based solution successfully guided management to focus their efforts and proactively remove bottlenecks.
    • The client gained or held market position in 400+ markets across 48 states while competing against larger and better resourced e-commerce and brand retailers in the United States.

    Technical Resources

    • DevSecOps, RPA, ARIMA, VAR, Agile process, Statistics SMEs, Commerce SMEs, On-prem system with a relational database engine, user-centered design, J2EE front end, SQL, SafeRock’s NetVantage solution, batch and BI reporting.

  • Analyze COVID for 1,000 cities

    Successfully Analyzed COVID-19 for 1,000+ Metropolitan Areas   Situation
    • SafeRock was engaged to analyze and model COVID-19 incidence across the United States for 1,000+ major metropolitan, suburban, medium metro, and micropolitan areas.
    Approach
    • We categorized over 1,000 US population centers by size and by proximity to urban centers. We related differences in COVID-19 case rates to social vulnerability factors. We further examined population migration, changes in the housing market, and levels of economic activity, in Los Angeles, Riverside, and San Bernardino counties.
    Result

    • We created accurate models of COVID-19 spread for the metropolitan areas and clearly identified specific outlier counties for further analysis. In the further analysis, we measured the correlations with voting patterns and socio-economic variables.

    Technical Resources

    • DevOps, MLOps, supervised analysis and reporting, Statistics SMEs, SAS, Agile team, AWS, Python, R and Shiny.