Tullow Oil - Information Flow Case Study
April 17, 2020 by Chandini
Over the last 6 months, we have spoken with hundreds of discretionary managers. One common theme that emerged is how reliant every team was on daily information flow to stay on top of their portfolio activity. These days, market moving Information could be anywhere - a product recall at your company's key supplier or a lawsuit against a subsidiary. Despite this, it isn't humanly possible to monitor information about a company to this extent. In fact, it might not even be feasible to manually find and link all the different bits of information.
There are now ways to make this aspect of your investment teams' research processes significantly more effective. To demonstrate how, here is some work we did with a PM for a top European Investment Management firm on one of their holdings - Tullow oil.
The Tullow Oil Opportunity
For the last couple of years Tullow has been trading sideways, but with enough movement to make money on short term moves. Then at the end of 2019, two large downward price moves occurred, leaving the stock 70% down within a month of trading. Obviously, this represents a huge short opportunity or a major loss, likely affecting firm level P&L.
On November 13, 2019 Tullow Oil (TLW) shares fell 27% after warning its production will miss targets following continued operational problems at its Ghana fields. Shares further plunged 60% on Dec 9 2019 to a 16-year low after the company surprised investors by slashing its production forecast for the fourth time in the year, due largely to lower production from the TEN and Jubilee fields in Ghana, scrapping its dividend and announcing that its chief executive and exploration director had left. The company’s market cap fell by more than $1 billion to $2.2 billion.
What’s interesting here is that the move was completely unexpected and came in a period where the market had the lowest short interest in the stock for almost a decade.
“Could we have seen this coming using data science?”, the PM asked us in a recent meeting. “Were there any early warning signals?”
A signal for issues to come
Using a knowledge graph, you are able to identify and rank news based on relevance to your a team's holdings and interests, even if it doesn’t mention the company directly. As long as the news is related to a company's key people, products, subsidiaries, suppliers, clients, competitors, risk factors and so on.
There were over 447,845 articles written between September to November in locations Tullow Operates across hundreds of publications. It would be impossible for a human analyst to search through these to identify any news that was relevant to anything in Tullow's ecosystem. The knowledge graph, however, does just this.
In this instance, the knowledge graph flagged this story from Aug 2019 as highly relevant to Tullow. Lessons to be learnt from Ghana's excess electricity shambles The model was monitoring not only Tullow Oil, but also Ghana National Petroleum Corporation (GNPC), Ghana Gas, who are clients of Tullow.
These stories from late October to mid November were also ranked high.
- Ghana Power Producers’ Debts Mount Over Arrears of $1.5 Billion
- Energy Surplus Leaves Ghana Paying for Unneeded Power
- Ghana Power Transmitter Owed $173 Million by State Companies
If we monitor media mentions, we can see (below) that there was a cluster of these articles released over the Autumn period.
Why is this the case and why is this important?
In this instance, the knowledge graph flagged Ghana National Petroleum Corporation and Ghana Gas as clients of Tullow and deemed it important enough to monitor and flag.
This cluster may have encouraged a team to dig deeper and form a hypothesis based on the potential impact on the company’s production figures. Sure enough, when Tullow cut production forecasts in Nov and Dec 2019, it cited low demand from GNPC as one of the reasons, adding that discussions on increasing gas offtake were ongoing, because increased gas offtake will reduce the amount of gas being reinjected into the fields, improving oil production over time.
The End Result
It would be impossible for all of a firms human analysts to search 500+ keywords relevant to Tullow through 100,000+ global news sources used by Auquan’s Portfolio Activity monitor, let alone read the 4.5 million news articles that could be significant. Yet within this mountain of data was significant alpha. If the PM or team had seen the articles flagged by Auquan, they would have been encouraged to dig deeper into their potential impact on any upcoming production figures. This, combined with other issues previously self-reported by Tullow, may have prompted funds to reduce their holdings or take a short position in the company.
This is just one example of how extensive monitoring and comprehensive coverage of news can help your teams identify opportunities within their investment universes. To quote one of our clients - “it’s impossible to track online information for every subsidiary of every company in your portfolio, especially across sources no one’s looking at”. Data science can make the process much easier. To find out how it could help your PMs, reach out to [email protected] for more information.
Share this Article:
Auquan is a data science solutions provider for asset managers and hedge funds. Our state of the art technology empowers Portfolio Managers to stay ahead of the trend and achieve better returns.