Artificial Intelligence

Time is money and, when trading financial instruments, a fraction of a second is all that stands between profit and catastrophe. That’s why investors, and hedge funds in particular, are using AI to mine massive sets of alternative data for insights that will give them the edge.

Successful trading has always relied on data and analysis – but such data has historically been composed of financial filings, investors’ reports and retrospective indices. These are interesting, but static. They’re no longer fit for purpose unless accompanied by alternative data, which draws in live demographics, current events, and a broad range of real-world trends to give the core financial metrics greater context.

Gathering and using alternative data

Grand View Research calculates that more than half of hedge fund managers use alternative data in their analysis and risk management. It gives an all-encompassing view not only of factors directly related to a particular fund or equity, but the environment in which it operates. As Krishna Nathan of S&P Global explained in the early days of alternative data, t “when you apply analytics to the data, they yield additional insights that complement the information you receive from traditional sources”.

“A well-known application of alternative data is satellite imagery analysis of parking lots, which is replacing the old-school approach of physical foot-traffic counts with clickers,” notes Deloitte. “In this case, alternative data approaches are faster and more comprehensive than physical counts, leading to an information advantage over the old-school approach – even though the data sets were measuring similar consumer activities.”

How Mortgage Lenders use Utility Data as metric proof

That’s far from the only area in which alternative data is helping businesses work faster – and smarter. The terms underpinning some US mortgages require loan recipients to live in a property for at least a year. Checking this manually would be an arduous process, which is why lenders are turning to utility data as a metric of proof.

It can also help applicants qualify for a loan in the first place. Many demographic groups have a poor or non-existent credit rating because they primarily manage their finances using cash, or don’t have a record of paying a mortgage in the past. This can put them at a disadvantage when applying for a home loan, unless alternative data like mobile phone records, utility bills and ongoing healthy balances in current accounts is used as an alternative to more conventional metrics.

How AI is used to read feelings and sentiment

At a more abstract level, sentiment analysis, which uses artificial intelligence and natural language processing to mine freeform data for opinion and feeling, can help decision makers to be more effective across many fields, including marketing and politics.

Automated analysis of social media posts, news media and reviews, among others, can be used to identify trends on the basis of semantics, and allow brand managers to tweak their campaigns in real time.

However, gathering broad metrics at speed increases the data points to be managed to an exponential degree – beyond the point where traditional methods and analytics software can cope. Equally, such varied data sets can be fragmented. That’s not to say they’re unstructured individually: weather reports and demographics follow set patterns, after all – but the differences between the two make comparing like with like impossible. It also makes deriving timely insights through manual, human analysis extremely unlikely.

AI is therefore required to spot trends and patterns across all data sets that, together, paint a more granular picture of the financial environment – and does so before the data itself becomes stale.

The benefits of artificial intelligence

Much alternative data, like road traffic conditions, satellite weather observations and government demographics, reside within the public domain. It can be imported directly or mined by scraping the web. Other data is bought in, and some is self-perpetuating such as when, through machine learning, the AI used to analyze alternative data gets smarter over time by analyzing its hits and misses without human intervention.

A large portion of the world’s trading is done by AI, here’s how

AI has the capacity to process this unbroken stream of fresh data 24/7, so can spot risks or execute timely trades when specific conditions are met, and give funds that employ it an edge. When deployed to the cloud, AI is cost-effective, too, as managers can spin up and decommission additional resources as and when required.

Not every metric will be relevant, so AI will also be tasked with filtering the noise before deriving insights from what remains that will answer a set question. When trading, the question is simple – buy, sell or hold – and AI will need to be trained using rules and a model for success against which to gauge its performance.

Use of AI in finance, outside of trading

Whether to go the final step and allow the system to trade on its own is a decision that can only be made by the fund manager themselves. Certainly, to extract maximum value from such data would be the most effective course. However, AI and alternative data have uses outside of trading like to mitigate risk, deliver supplementary insight for human consumption, or as a proof-of-concept tool for use in a broader ongoing development.

Artificial data finance

Artificial data is rarely discussed outside of traditional financial circles, and its scope puts it out of reach of solo and small investors, as getting started requires significant resources and expertise.

However, fund managers know differently, and understand that ongoing investment is their only option – and one of the few costs that’s guaranteed to deliver significant returns right away.

Unless you’re using alternative data in your day-to-day analysis, you’re only getting half of the story. Contact Merit today , and learn more about the tools that will deliver the insights you need to take your business to the next level.

Case Studies

  • 01 /

    Automotive Data Aggregation Using Cutting Edge Tech Tools

    An award-winning automotive client whose product allows the valuation of vehicles anywhere in the world and tracks millions of price points and specification details across a large range of vehicles.

  • 02 /

    Digital Engineering Solution for High Volume Automotive Data Extraction

    Automotive products required help to track millions of price points and specification details for a large range of vehicles.