Oil & Gas Case Study
Summary
A leading ethanol marketer and producer uses River Logic's Enterprise Optimizer® (EO) Decision Engine to optimize its commercial and operational planning decisions. The company faced an extremely complex logistics and inventory management challenge, which is common in the downstream oil and gas sector, and wanted more collaboration between its operations and trading teams. It now has a fully integrated planning solution.
The commodity trading and logistics optimization solution, built on the Decision Engine, lets logistics planners easily optimize transportation schedules and inventory strategies for a given set of contracted demand, and re-optimize in light of strategic what-if scenarios. Traders can proactively identify market opportunities that go beyond traditional price arbitrage and improve return on the firm's existing transportation and inventory assets.
Immediate results yielded $12 million in profitability improvement opportunities related to current contract fulfillment, and the firm estimates total net-back gains of $0.01 to $0.02 per gallon, annually.
Company Overview
A Fortune 500 international manufacturer and marketer
The company, a Fortune 500 international manufacturer and marketer of transportation fuels and other petrochemical products, produces and distributes large volumes of ethanol throughout the United States. It operates multiple high-velocity production facilities, and its traders buy and sell future share contracts, which are typically fulfilled from regional third-party terminals.
The Challenge
Traders and logistics planners were under constant pressure to satisfy several complex, interrelated supply and demand constraints intrinsic to a commodity-based business model. Executive management, meanwhile, kept a careful eye on the firm's strategic objectives, including overall portfolio profitability and total return on assets. Despite the extreme complexity of the combined logistics scheduling, inventory management, and market trading problem, traders and logistics planners had no cross-functional view of customer demand, product sourcing, storage, or transportation.
[Image: Figure 1. Supply and demand dynamics driving complexity in the company's logistics and inventory value chain.]
The complex logistics and value chain network caused these challenges:
- Inaccurate representation of constraints: Spreadsheet models of the value chain failed to represent the impact of constraints and decisions accurately.
- Money left on the table: Spreadsheets made it impossible to analyze all possible decisions simultaneously, which led to suboptimal outcomes.
- Inefficiency: Building and maintaining spreadsheets took significant time from planners and traders, limiting productivity and collaborative analysis.
- No collaboration: There was little to no collaboration in ongoing planning. Each trader developed his or her own insights through traditional arbitrage approaches that routinely failed to fully use the firm's transportation and inventory positions.
- Lack of agility: Responses to unplanned events were inefficient and ineffective.
Because logistics and inventory variables and constraints were not properly represented in trading decisions, the business knew it was leaving significant net-back dollars on the table. It looked for a solution that would:
- Make it easier to identify and understand the complex trade-offs in its value chain
- Give planners and traders the knowledge to plan, execute, and track integrated commercial operations strategies aligned with corporate objectives
- Enable greater agility and collaboration in commercial operations processes
The company wanted an agile, forward-looking planning solution that could account for the millions of variables and constraints across its end-to-end business while drawing data from existing systems, including its ERP, TMS, and Energy Trading & Risk Management system.
It selected River Logic because it was the only optimization platform that met these needs while also enabling the cross-functional collaboration required to finally retire the piles of spreadsheets the company had relied on for so long.
The Solution
The solution is built on a model of the business in the EO Decision Engine. The model represents how the business actually works, including how it earns revenue and incurs cost. The engine then finds the provably best way to meet all key objectives while respecting important cross-functional limits, such as customer SLAs and inventory holding capacity thresholds. Logistics planners, traders, and executives create and analyze unlimited what-if scenarios in a cloud workspace that includes editable master data input forms and embedded Microsoft Power BI reports.
[Image: Figure 2. The model of the end-to-end business in the Decision Engine, showing how it works from sourcing through storage, transportation, and customer demand.]
The EO Decision Engine met all of the firm's technology needs:
- One model of the business: A model that can easily be expanded or modified as business needs change
- Integrated financial modeling: The ability not only to manage but to optimize the business's complex, interrelated contractual, physical, and financial constraints
- A view into marginal opportunities: The ability to proactively identify and quantify marginal opportunities beyond traditional price arbitrage
- Performance management: The ability to create optimized logistics schedules, inventory strategies, and trade execution playbooks, track progress against plan, and manage the planning process with easy-to-use workflows
Real-Time, Optimized Answers
All plans now reflect the company's current reality. Scenarios can be quickly modified to reflect market changes or new internal constraints, and the company saw immediate value from answers to questions it previously could not answer:
- If we have a plant outage or capacity reduction, how should we re-optimize the logistics plans? What are the costs? Which risk mitigation strategies, if any, should we pursue?
- Which products, customers, and contracts make us the most money? What is the best way to expand our positions in these markets?
- When and where do we have excess transportation capacity, and what does that mean for our potential return on assets relative to current forward price markets?
- When commodity prices fluctuate, where are the opportunities to trade based on profit and our current positions?
The Impact
The company can now optimize logistics plans for the demand under contract and then quickly identify opportunities to better monetize transportation and inventory. This information goes to traders in near real time, so they can make better-informed market decisions that use the opportunities created by the company's optimized supply chain. The result is a significant competitive advantage in the ethanol market.
From a financial perspective, immediate results include $12 million in profitability improvement opportunities on current contract fulfillment, and the firm estimates total net-back gains of $0.01 to $0.02 per gallon, annually.
The company currently analyzes these scenarios daily:
- Contract profitability
- Optimized contract fulfillment
- Plant closure / temporary shutdown
In the future, it plans to look at:
- Delivery day: The cost of delivering on a specific day versus a delivery window
- Unplanned outages: The cost of unplanned plant outages, quick re-optimization to adapt, and whether outages should be addressed with ST or OT labor
- Fleet size: The optimal fleet size to serve current and potential demand
- Asset utilization: Under-utilized assets, to evaluate future strategies
- Contracts: The impact of new contracts (purchase, transportation, sales, etc.)
About River Logic
River Logic builds the Enterprise Optimizer® (EO) Decision Engine, which turns business goals into defensible, execution-ready decisions, each with the receipt: the binding constraints behind it and a trace back to the source data. Built on 25+ years of optimization R&D, one model of the business answers questions across planning domains, from network design and capacity to product mix and capital allocation.






















