Deep Learning/Machine Learning Technical Interest Group (TIG)

Applying new analytics, neural networks, computational approaches using structured and unstructured data, and also training neural networks with supervised and unsupervised algorithms. Chaired by Patrick Ng and Andrew Munoz.
Deep Learning - Machine Learning TIG
PrevPrev Go to previous topic
NextNext Go to next topic
Last Post 23 Oct 2019 01:10 PM by  Patrick Ng
Drill down into risk and return using Hybrid model - from DCA to MPT
 0 Replies
Join to post a reply.
Author Messages
Patrick Ng
New Member
New Member

23 Oct 2019 01:10 PM
    Highlights of examples shown at the AAPG ML Workshop, Wichita KS two weeks ago.

    Hybrid model combines neural-network enabled decline curve analysis (DCA) and modern portfolio theory (MPT). We illustrate a powerful methodology to quantify risk and optimize portfolio allocation with granularity, integrity, transparency and science-based machine learning in mind.

    Examples using the same AI engine

    First quick check on Hart Energy Majors portfolio (six stocks, ). Determine the max risk-adjusted return (Sharpe ratio) is Chevron. Calibration - Barron’s “Lowest Risk and Best in Class”, August 21, 2019

    Next, instead of financial assets, focus on real assets - petroleum basins, Bakken, Eagle Ford, Marcelleus and Permian. Recall “Hybrid approach to Well Economics”,
    published in July 2016: a) min variance portfolio - overweight Eagle Ford and Marcellus (i.e., light oil and gas rich, respectively); b) max Sharpe portfolio - all in Eagle Ford. Calibration - “Eagle Ford is weathering volatility better than most oil fields”, September 26, 2019.

    Conclusion - Hybrid model advances quantitative risk management and strategy development in energy transition.

    Relevant reading -
    Join to post a reply.


    Andrew Munoz Ensign Natural Resources
    Patrick Ng Real Core Energy

    Headquarters Contacts

    Susan Nash Director, Innovation and Emerging Science and Technology breeling