So much data, so little time. How Predictive Analytics uses Big Data and simplifies trading decisions.
By Steve Krawciw, CEO of AbleMarkets
Most investors would like to understand the drivers of performance if their portfolios in order to incrementally improve their allocation decisions. One way to identify what is truly behind their portfolios’ returns is to compare the performance of portfolios vis-a-vis benchmarks.
In the past, the available benchmarks were few and far between, easily manageable in one Excel spreadsheet. In the last decade, the number of data sources needed to be taken into account have multiplied dramatically, requiring databases and dedicated staff to manage the data and to analyze it in reasonable time. An alternative to buying and processing more and more data is to delegate the data attribution to a new industry, predictive analytics.
What is predictive analytics? The advances in data science allow real-time processing of a massive, previously unthinkable, amount of data. For example, it is now possible to process all order data from an exchange, not just trades but every market, marketable and limit order for every electronically traded instrument.
Advanced big data models allow scientists to create highly-intelligent algorithms capable of answering questions far more complex than traditional regressions or segmentation frameworks. These algorithms cut through the non-trivial task of making sense of mountains of fundamental data by providing an index that answers a question. For instance, many investors and traders charged with execution want to avoid trading when aggressive high-frequency algorithms are present. Companies like AbleMarkets now tease out aggressive HFT out of streaming data and show in real time when to speed up trading and when to slow it down. Such technology, unthinkable just a decade ago, is now not only feasible, bu available to all to use.
What is driving the increase in available data? In the past, data storage and data processing were too slow and too complex for any reasonable business application. As a result, much of the market data was simply destroyed. Modern computing power, storage and transmission now allows to store and review limitless amounts of market data. Further, analysts are now also looking to the “internet-of-things” for insight. These include all information from applications like tolls, weather stations, freight ship tracking systems, iPhone usage, etc.
Not only has the supply of data grown, but the types of people using all of this data are changing too. The traditional roles of exchanges, brokers and data providers are overlapping each other as their business models change and they are all trying to position themselves as a value-added partner to the trader by providing some form of analysis platform. Since asset managers don’t have time to explore all new data sets themselves, they reward vendors who can provide useful ways to analyze data.
Companies like AbleMarkets make it easier for analysts to make use of large data sets by doing the hard work to develop algorithms that analyze the data and inform the analyst of insight when the algorithm finds it. Able Markets generate indices that are like ETFs in real-time.
Are feeds replacing platforms? As the amount of data grows, asset managers are placing a more strategic emphasis on data. This makes the reliance on Bloomberg or Reuters more than a simple outsourcing decision. Large asset managers are considering whether the structured platforms fit with their need for a broader and deeper library of data feeds.
Reuters, for example, offers clients the ability to use their platform or to receive data feeds directly. The value of a Reuters or a Bloomberg become more questionable with new players like Quandl offering data feeds at very low prices. Quandl considers their open platform to be a “democratization of data”. By bringing all numerical data into one place and building a smart index and interface Quandl opens up quantitative information to everyone. Quandl claims to offer 4 million financial and economic time series for free.
Many asset managers prefer to receive data feeds directly. When a specialist like Able Markets works with an asset manager, the frequency of downloading data becomes important and having to work through a third-party platform often just creates latency issues.
How do predictive analytics transform data into insight? Portfolio managers use performance attribution to explain why a portfolio’s performance differed from the benchmark. This review of historical trading attempts to distinguish which of the two factors of portfolio performance, superior stock selection or superior market timing, is the source of the portfolio’s overall performance.
However the past is not necessarily an indicator of the future. Looking at benchmarks do not necessarily capture the full picture of what is happening in the markets. Able Markets uses an approach of continuously review the markets for indications of that there is an opportunity to trade, whether become of changes in sentiment or because some aspect of a market’s microstructure that is highly predictive of either price movement or changes in volatility. The ongoing analysis generates an index and these indices help to guide trading decisions.
As the volume of data expands and is offered more rapidly, the portfolio managers needs to take advantage of new ways to harness data without doing all of the analysis himself. Predictive analytics is one answer emerging in the marketplace.