By Shahil Kotecha and Prabhay Joshi, financial services experts, PA Consulting Group
Social media networks, such as Twitter, Facebook and LinkedIn, provide us with constant and direct access to the thoughts and ideas of millions of people around the world. This thinking is hugely valuable when it’s monitored, analysed and transformed to provide advantageous insights.
Companies across all industries have recently been realising the value of ‘social intelligence’. The interpretation of this big data has meant they are reaping the benefits of being able to understand their customers’ behaviours more clearly. The insurance industry, for example, has successfully used social analytics for fraud prevention and to improve the prediction of their customers’ risk estimates. Apple meanwhile, analyses Twitter feeds in real time and gleans customer sentiment and trends to strengthen its consumer propositions.
It’s now the investment industry’s turn to follow suit. Several institutions are already attempting to use social intelligence for real time identification of consumer sentiment towards an industry, geography or a particular company. Saxo Group, for example, has recently launched TradingFloor.com, which allows traders to follow each other’s thoughts. However, the sheer volume and complexity of the analysis has meant that any attempt to use social data in this way has been confined to a limited set of firms who have the right technology and expertise. Even less prevalent is the application of behavioural analysis to social data. When done accurately, this process can be a highly effective way to forecast likely consumer behaviours and, as a result, predict demand-driven financial market trends. Bridgewater, the world’s largest hedge fund, is already using Twitter feeds to model economic activity but the rest of the market is yet to follow suit.
WANT TO BUILD A FINANCIAL EMPIRE?
Subscribe to the Global Banking & Finance Review Newsletter for FREE Get Access to Exclusive Reports to Save Time & Money
By using this form you agree with the storage and handling of your data by this website. We Will Not Spam, Rent, or Sell Your Information.
The ability to mine this social data provides an unprecedented and pioneering method of validating investment strategies through the prediction of consumer behaviours:
By collaborating with social data specialists, investment managers have the ability to use a filtered social data feed as a leading indicator to identify emerging themes that impact their respective investment portfolios. This can be achieved by mapping out social themes that are linked to key asset allocations; sectors, companies or geographies within a portfolio.
On a simple level, an equities fund manager may have a tactical position in Apple, and can therefore benefit by understanding developments related to them. They could break this out in to the following social media key words: “Apple” (the most direct) as well as “iPhone,” and “Mac” (associated products that are likely to be discussed on social media). An algorithm can then be created to cut through the flood of potential data available and deliver the aggregated consumer sentiment towards these words. This process of assigning social themes can incorporate further detail as needed, for example, the equities fund manager may want to track sentiment towards competitor key words such as “Samsung” or “Nokia” in the algorithm. The key part of sentiment analysis is tracking not only the themes that are discussed (and how often they are discussed), but also the feeling towards these themes.
But does consumer sentiment towards an industry or a company actually matter when it comes to financial markets? When sentiment analysis is enhanced to add behaviour prediction, the answer is yes. Overlaying behaviour analysis on top of it enables one to predict how consumers will act in the future, and therefore how financial markets may react. This involves understanding what a given sentiment indicator implies about future consumer behaviour. According to the study, “Twitter mood predicts the stock market”, Twitter sentiment correlates with the ups and downs of the next few days on the Dow Jones Index with 87 percent accuracy. This shows how sentiment indicators can be important in predicting short term market movements. But sentiment analysis should not just be limited to short term investing.
Analysing sentiment indicators over a longer time can offer important insights in to consumer spending trends, and therefore company revenue movements, which will have a direct impact on stock prices. Such correlations can be represented in a simple visual dashboard that is updated in real time.
The value of this output means investment managers have an unparalleled source of information against which to compare the results of their conventional investment research. It is a validation tool that allows managers to make informed decisions that take into account a ‘live’ barometer of the consumer world. Whilst investment managers might not drive their investment strategy directly from sentiment indicators, this approach will enable them to determine a complete picture of the factors contributing to their investment performance. A holistic approach to investment analysis would include conventional technical analysis conducted on historic data alongside real-time social media intelligence. As we move forward, social intelligence is likely to be an integral component of any investment manager’s risk mitigation against global events and consumer trends.
Investment managers that build social intelligence into to their investment infrastructure early on will help close the gap between themselves and the likes of Bridgewater; those that don’t, may find that they can’t compete.
For more information, visit www.paconsulting.com/financialservices
Follow PA on twitter @PA_Consulting