Connect with us


Time Series Data Reveals Insights to Inform Investment Decisions

By Stuart Tarmy, Global Director of Financial Services Industry Solutions, Aerospike

In today’s capital market, investment firms must manage and analyze huge volumes of historical and streaming data (“quote data”) to help forecast market trends, test trading strategies, trading, manage risk, identify high alpha trading opportunities and comply with industry standards. regulations. This can be particularly time-consuming and data-intensive due to the chronological nature of market data.

In the investment industry, time series data is a sequence of data points, such as the price of a security, tracked over a specific period of time. Investors analyze time series of tick data, that is, data for every trade in a given security. Tick ​​data includes security symbol, execution price, lot size and timestamp. Other information often included in tick data is the security exchange and the security industry sector. Quote data is available for many different types of securities, including stocks, bonds, ETFs, mutual funds, options, derivatives, and futures.

That’s a lot of data. For example, a capital market firm may want to store every transaction of a particular firm every day for seven years. And then do that for all the other stocks. FirstRate Data, a provider of high-resolution intraday data on stocks, crypto, futures and currencies, says it has archives that include trade and quote data for over 4,500 tickers aggregated out of 12 scholarships. The total archive is approximately 200 terabytes of uncompressed data.

Understanding Time Series

Forecasting is one of the main uses of time series. Capital market firms build models with historical tick data to identify future trends and directions – with the idea that understanding the past will predict the future.

Time series analysis can be used to detect patterns and trading opportunities within a given asset, within a given asset class, or across different asset classes. As an example of observing patterns in various asset classes, investors may want to compare the movement of a company’s stock to the movement of its bonds at different maturities. They might see bond prices deteriorating or indicate bond downgrades by bond rating companies, giving them insight into what might happen with the stock’s future performance.

The main behaviors of time series are trends, seasonal variations and cycle. A trend is a pattern in the data that reveals an increase or decrease in the series over a long period of time, and which does not repeat itself. For example, a capital market firm may want to analyze a stock’s daily closing price for a year to help gauge its performance. Seasonality is when patterns or cycles repeat themselves regularly over time. A capital market firm may wish to analyze a stock’s time series to see if drastic highs or lows are correlated to a particular season, whether it be the traditional calendar or retail holiday seasons. Cyclical behavior occurs when the price of a stock rises and falls due to economic conditions such as the unemployment rate or interest rates. Fluctuations are not a fixed frequency like seasonality.

It can be useful to measure the evolution of a given asset, security or economic variable over time. Leading quantitative trading firms use time series to find actionable patterns in tick data to guide their investment decisions. Financial theory states that the performance of a stock is tied to the underlying market (beta) and the specifics only to that stock (alpha). They look for alpha and beta measures to gauge a stock’s performance. Analyzing time series data can help identify alpha to see how a stock performs independently of the market.

A number of progressive, research-driven asset management firms are also developing quantitative capabilities to overlay their investment research to see if it’s a good time to make a purchase. These companies have learned that even though they may discover a great company to invest in and the price looks attractive relative to the expected cash flow, the stock price continues to decline due to the influence of quantitative trading. It ends up being a losing trade. Although they may not understand it or approve of it, they have come to realize that quantitative investing influences their business decisions and results.

Managing Time Series Data

Capital market firms using traditional data architectures struggle to quickly store and analyze massive amounts of time-series data. This type of data accumulates quickly because each record is a new measurement at a specific time interval that is added to the existing data set. It is not simply an update of an existing registration. Not only is there a huge volume of data, but the list of data sources is long when it comes to accounting for investments in the different asset classes.

Traditional data architectures can’t keep up because they weren’t designed to handle the real-time scale and complexity of large-scale data (terabytes, petabytes). They can suffer from high operational costs, unpredictable performance, inconsistent data, latency, and availability issues. Delays in accessing and processing time series data can lead to incorrect or incomplete investment models, degrade investment performance and introduce additional risk.

On the other hand, modern data platforms have been designed to solve these problems in order to efficiently store, retrieve and process real-time time series data. These platforms contain the latest processor, storage, and networking technologies, and use scalable, geographically distributed architectures to better handle growing data sets.

These new platforms include three key capabilities that allow companies to adapt to real-time market conditions and build and deploy their forecasting models. They can 1) quickly ingest data from multiple data sources, 2) develop and train sophisticated analytical models, including artificial intelligence (AI) and neural networks, and 3) deploy them to production environments in real time.

Modern data platforms are now available to enable financial markets firms to unlock the value of time series data – revealing insights to inform data-driven investment decisions and better manage risk.

Stuart Tarmy is the Global Director of Financial Services Industry Solutions for Aerospike. He has over 25 years of experience as Managing Director and Head of Sales, Partnerships and Product Management for the world’s leading financial services technologies, electronic payments, e-commerce, artificial intelligence/learning automation (AI/ML), data privacy and regulatory compliance. companies. He has held senior positions at Fiserv, MasterCard, Bankers Trust and McKinsey & Company. Stuart began his career as a design engineer at Texas Instruments, developing AI/ML-based computer systems. Stuart holds an MBA from Yale School of Management, a Masters in Electrical and Computer Engineering from Duke University, and a Sc.B. with honors in Electrical and Computer Engineering from Brown University.

#Time #Series #Data #Reveals #Insights #Inform #Investment #Decisions

Click to comment

Leave a Reply

Your email address will not be published.