These online demos are not supported on a mobile device.
This website is not supported by Internet Explorer - please consider using the latest browser

Portfolio planning

Problem

Business Problem

A government and National Oil Company face a complex portfolio planning decision regarding upcoming exploration licensing rounds.

The NOC is a 35% shareholder in all development and exploration licenses.

The investment portfolio is large, ranging from unexplored blocks to ongoing developments.

The country's GDP is very dependent on Oil & Gas. Political and public expectations are high but the growth pace is putting strain on the NOC's cashflow.

New exploration licenses have varying probabilities of success, mean success volumes, development cost and timelines to discovery and first production.

Goal

Use Game AI to build optimised plans from different stakeholder perspectives to give insight into the decision.

Scale Over 50 unexplored blocks can be put out for bidding, There are millions of combinations to consider for upcoming license rounds. Different Drivers A healthy balance sheet is important for the NOC but may be a possible constraint for government income. Political pressure to discover new volumes is high, but may conflict with activities that aim to maintain the production plateau. Uncertainties Most input to portfolio planning is uncertain. Mean success volumes, probabilities of success, schedules, cost and production - none are exactly known beforehand. The result is a highly complex challenge - manual portfolio analysis is bound to be suboptimal. Result

Portfolio planning

Process

Game AI

We translated the country's exploration bid around planning into a game, and taught an AI agent to play this game.

Through self-play, the AI learns to master the game mechanics and to develop strategies that outperform human planning capability.

Using our AI as assistant, we can now develop long term strategies for upcoming licensing rounds while taking into account different stakeholder views.

Learning
the basics
of the game 0 GAMES PLAYED

Portfolio planning

Dashboard

Drivers

Use the settings below to reflect what you feel are the most important drivers for the country and NOC. Evaluate how different drivers lead to different optimized licensing rounds and outcomes. Use this insight to make the "right" decision.

Is external funding
acceptable for NOC?

OK to
lend money

Maintain
production plateau

not a driver

Discovered volumes
(100%) in next 5 yrs

not a driver

Government income(5 yr, bln USD)

14

Discovered volumes(5 yr, mmboe)

527

Exploration licenses issued(5yr)

11

Licenses

NOC Production

NOC Free Cash Flow

Back
Load the
Game AI