Leverage Predictive Analytics


Our promotion optimization system measures the baseline and ad lift of your promotions, so you can understand the exact sales and profit impact of each promotion, and your most and least profitable offers. Equipped with this information, Marketing and Merchandising can make better decisions that improve customer response at all touch-points. 

For brands and retail, our predictive algorithms accurately forecast total item and category sales. 

In the energy sector, we use predictive analytics and machine learning algorithms to forecast oil and gas production for public and private operators. Our system contains custom decline curves for over 15,000 wells in Eagle Ford and Permian. We dynamically generate forecast new well output, as well as EUR and future production for any collection of wells.


To improve total profits
Use our ‘best in class’ promotion optimization system to increase store and online traffic, total sales, and gross profits. We help increase ROI for marketing and merchandising. 


  • Engagement: Increased Profits and Sales at Multichannel Retail

    -A $5+ billion dollar North American retailer wanted to optimize promotions and build a system to continuously improve merchandising and marketing ROI.
    -The goal was to improve investment and budgeting decision. This is an international chain of department stores.

    -Working with the CMO, CIO, and merchandising and marketing teams, we developed an ROI-based strategy to improve promotion effectiveness. Our joint team designed a cloud-based ‘Big Data’ solution to measure promo effectiveness with extreme accuracy. The system analyzed over 100 million records for 1+ million SKUs, using 500+ simultaneous seasonal models. Our system and algorithms were integrated with Oracle™ and Teradata™. 

    -The solution delivers precise KPIs that ‘sheds light’ and allows accurate performance comparison across all merchandise categories. Due to its extreme accuracy, our system became the ‘system of record’ for the company. Users include senior management, (CXO, GMM and DMM) and all merchandising and marketing managers. 

  • Engagement: Improved Buyer Planning and Increased Customer Satisfaction

    -The specific challenge for an $8 billion category specialist retailer with 500+ stores was to improve buyer sales projections. Frequent stock-outs of ad items were turning customers off. This had impact on supply chain and inventory costs.

    -Our approach was to work with supply chain, IT, marketing, and marketing to gather item, ad, and category sales information and use this to evaluate performance. We then built a system for reporting ad performance on the item, category, and department level. We generated actual vs. forecast measures, ROI, and ad lift. We combined sales data for all ad items with total sales and entire category sales, as well as item pricing, ad space allocation.

    -Working with a singular strategic plan, we worked successfully across multiple company teams and tiers, we built a powerful system that generated highly forecasts and improved buyer forecasts.
    -In addition, we successfully analyzed item and category sales and improved buying and inventory.

  • Engagement: Improved Customer Journey and Top-line Sales

    -A $500 million chain of 40 regional supercenters had ineffective ad performance. They needed to improve lagging ad sales and store traffic, and reduce out-of-stocks. In addition, vendor funds were not efficiently managed, with millions of dollars being lost each year.

    -Our approach was to work in a team across merchandising, advertising, and vendor fund management groups. We measured ad lift by item, volume and profit; and estimated square-inch returns. This created an analytics-based process for item selection.

    -Identified ‘cherry-pickers’ and capitalized on this to draw shoppers to stores.
    -Optimized ad space allocation.
    -Recovered millions in ‘leaky’ vendor funds.
    -Successfully delivered analytics-driven ad item selection for top items.
    -We increased vendor fund use by over 10% for over $20 million. The new system automates the image management, ad pricing, and multichannel marketing.

To be more effective
Using our analytics and systems, you can improve your ROI at all customer touch points, including mobile, store, and omni-channel. 


  • Engagement: Enabled Digital Transition Leading to Greater Efficiency

    -A leading non-profit organization that provides economic and financial education to K-12 students wanted to know how to create digital content, expand its e-learning platform, and increase engagement. The non-profit works with 50,000+ teachers across the United States who teach over 5 million students.

    -We worked with the COO, the VP of Content, and IT resources on putting the digital transition in place.
    -Our team provided strategy, project management, digital content, e-learning goals as well as technology.

    -As a result of our work, the non-profit was able to successfully transition from print content to digital and mobile while keeping to their timeline and budget.

  • Engagement: Improved Multichannel Marketing and Customer Satisfaction by Eliminating Pricing Errors

    -A national retailer wanted to eliminate information errors at all customer touch points, including print, mobile, coupons, offers, and POS. They wanted to eliminate pricing errors that were disheartening consumers and creating confusion at stores.

    -We established systematic ways to ensure correct price maintenance across all marketing channels and all customer touch points.
    -We installed a system that caught promotion mismatches over multiple marketing channels, flagged incorrect product and price information, and ensured price consistency for 22 states simultaneously.

    -Our system successfully eliminated product, promotion, and pricing errors and ensured correct product information at all customer touch points.

  • Engagement: Created Competitive Advantage for National Content Developer

    -A national provider of testing, content, and training services with presence in over 30 states needed a new strategy to repurpose and effectively deliver content to new markets.
    -This new solution had to be engineered within 6 months.

    -We engaged the President, COO and several Executive Directors for a company-level P&L review.
    -We followed this up with detailed program plans for a new product introduction, with all teams aligned. There was a six month transformation process to improve decision-making, teamwork, and ROI.

    -We successfully solved the technology problem to allow solution delivery within 6 months, well ahead of competition.
    -The solution automatically distributes to customers using a new delivery platform.

To attract new customers, protect existing markets, and increase sales
Use our versioning system to segment price zones and localize markets. We can show you how to customize items and offers down to the store.


  • Engagement: Improved Market Segmentation and Return on Marketing Investment

    -A $6 billion regional chain of 400+ supermarkets was facing stiff competition due to competitor store openings and internal inability to resolve weekly ad space allocation issues. This led to weak marketing performance.

    -We worked with both IT and merchandising to gather item, ad, and category sales and link this to space allocation. We crunched weekly sales data across all ad items at the store level, and systematically combined this with information on item pricing, ad space, and category space allocation on regionally versioned weekly ads.

    -The system Identifies category winners and losers.
    -Ranks weekly sales for ad performance.
    -Prioritizes ad space allocation for merchandise categories.
    -Successfully improved ad space allocation.

  • Engagement: Bridged Merchandising and Marketing ‘Silos’ to Improve Competitiveness

    -This $12 billion, 800+ store national retailer wanted an enterprise system to share financial and product information, and to bridge the gap between departmental ‘silos’. Management needed access so they could provide proper oversight, improve P&L, and document vendor fund use.

    -Working with Marketing, Merchandising, and Finance, we designed and implemented an Oracle-based central store of data for sharing of information across departments.
    -We installed the solution and conducted training for all users.
    -We then migrated item, copy, and price information to the online system.

    -We successfully managed over 2 million store-level item price points.
    -Bridged the departmental ‘silos’ of Merchandising, Marketing, and Finance with a single workflow system.
    -We successfully decreased out-of-stocks on promotional items and established a single system of record for promotions and marketing events.

  • Engagement: Improved Sales Analysis and Promotions, made Better Use of Vendor Funds

    -A regional supercenter chain in the Northeast US wanted a scientific, analysis-driven, system that would improve Merchandising’s item selections and promotion planning. They also wanted to simultaneously link marketing and co-op funds.

    -Our approach was to measure ad lift by item, volume, and profit. We estimated square-inch returns and created an analytics-based advertising process.
    -We estimated square-inch returns and created an analytics-based advertising process.
    -The new process went from merchandise review and item selection, to FP&A improvement, and marketing efficiency.

    -Our solution successfully delivered analytics-driven ad item selection for the top 1,000 items weekly. It improves promotional fund tracking, and automates versioning of marketing messages across all customer touch points.


  • Calculates EUR for oil and gas wells
  • Automatically spots anomalies, outliers, and re-completions
  • Forecasts expected production for the next 1, 2, and 6 months
  • Uses machine learning to calculate an optimal ARPS decline curve for each individual well


  • Project: System beats market consensus to the punch and forecasts gas and oil production

    – A top-rated US energy analyst firm wanted to improve production forecast accuracy for public E&P operators in Lower 48.

    -Using purely public data, we built a unique process using proprietary algorithms that takes well-level monthly oil and gas production data from E&P operators and builds dynamic models for each and every well.

    -The new system improved accuracy of forecasts by 2/3.
    -It dramatically shortened calculation time for estimating EUR and production forecasts for oil and gas.
    -It provides KPIs, well production profile, and production forecasts for oil and gas.
    -The process proved to be a true data-driven process that completed forecasts by 1,000% faster than before.

  • Project: System beats Experts in forecasting accuracy

    -The challenge was to improve the accuracy of EUR estimates so that our system could be more accurate than EUR calculated by engineering experts.

    -We agreed to build an automated system for calculating well-specific EUR. The ARPS model was used as a base.
    -We had engineering EUR estimates of several hundred wells, and the goal was to estimate this more accurately than an expert using the same data.

    -The new system was more accurate than expert estimates over 2/3 of the time in three different sets of well comparison.

  • Project: Custom Type Curves created for any set of wells

    -Type curves are used almost universally in the energy industry to estimate area production, new well output, represent production profiles, in corporate reports. However ,their limitation is that it cannot distinguish on a finer basis.
    -Our goal was to generate dynamic type curves for any given set of wells.

    -We built an automated system to calculate a custom Type Curve for any given set of wells.
    -ARPS model was used as a basis for calculation.
    -The significant advance was to taken any set of wells _ from 2 to 2,000 – and automatically generate representative type curves.

    -We succeeded in building dynamic type curves that were more accurate than existing static curves in predicting output.

  • Project: Fast Big-data System rapidly models one new Well per minute

    -The challenge was to turn around well estimates faster than traditional methods while maintaining accuracy.

    -System took standard public data, made APRS based models, and ensured best fit to historical production.

    -Generated dynamic well models at the rate of one per minute.
    -This process is systematic and automated, and produces unbiased results.


  • Integrates marketing and merchandise planning with online traffic to reduces out-of-stock
  • Accurately forecasts retail sales using predictive algorithms and machine learning
  • Improves both marketing ROI and return on ad spend


SafeRock spots Carrizo’s (NASDAQ: CRZO) stock surprise 2 months in advance

News Update
News Update: 
February 28, 2018 
On February 26, 2018, Carrizo’s (NASDAQ: CRZO) stock tumbled -23% and the company reduced the value of its Eagle Ford EUR assets by -14%. SafeRock had identified Carrizo’s production anomalies in December, two months earlier.