Using Alternative Data for Short-Term Forecasts

Rate this post

Opinions expressed by Entrepreneur the collaborators are his.

Alternative data is no longer a secret, especially in the financial sector. New and unique data sets were always in sight of investment firms, hedge funds, venture capital firms, and so on. A good example of the upward trend is ESG data, which seems (so far) to provide tremendously powerful signals for investment decisions.

While there are many alternative forms and forms of data, the most widely used and researched is sentiment analysis. Web scraping is relatively easy to access nowadays, making the acquisition of these data sets economical and efficient.

Sentiment analysis, for example, has been shown above to be able to generate valuable knowledge. With the data surrounding it, however, it’s easy to be fooled by the supposed potential it has.

Related: Understand market anomalies using alternative data

Feeling and other alternative data types

Few articles have dealt deeply with the concept of feeling. In most cases, it is the automated processing of content (usually text-based) to obtain emotional states and judgments. Advanced tools such as Google’s natural language AI can discover sentiment, assign entities (objects being talked about), and so on.

Investors ’emotions and sentiment have a clear effect on the stock market. The impulse effect is a great example of the medium-term market inefficiencies caused by the emotional context of investors. The two forces underlying the impulse effect, overreaction and overreaction, are essentially based on emotional states.

However, an important caveat that I rarely see mentioned is that emotional states are not long lasting and can only provide predictions for extremely short time windows. In fact, as I want to show below, most, if not all, alternative data collect a short-term forecast (less than 5 years).

Investors and companies

From a bird’s eye view, stock prices are affected by investors and issuers. The former have a direct impact on price, as they are the engine of demand. The latter have an indirect effect, because business performance has an impact on investor perception and stock valuation.

There are also possible black swan events that could upset the balance at stake. However, I will not talk about them, as I would add many unpredictable variables to my hypothesis without providing much additional value.

Companies have an indirect impact on both short-term and long-term prices. Current cash flows, consumer sentiment, marketing strategies, etc., can have an impact on quarterly or annual earnings. Business strategy, growth options, and other factors influence long-term performance.

Xerox has always been an example of how a changing business strategy and competitive landscape can have a huge impact on an organization’s performance. He has held dominant positions in the market and has struggled for decades.

Because the company’s performance and stock prices are closely tied, expert investors need to consider the short- and long-term outlook. Alternative data, however, contain mainly information about the former.

Related: How to forecast revenue and growth

How far can alternative data go?

Various sources of information can be called alternative data because they are so vague. However, it will mostly be scraped web information, satellite imagery and credit card data, as they are among the most used sources.

Each of these sources, whether it’s collecting feelings from public social media posts or analyzing cash flows through credit card data, points to the current state of the business. In other words, it is a reflection of current performance. Also, these sources are not supposed to be long lasting. They are snapshots of a decidedly short period in the history of the company. The data must be collected over a longer period to make any kind of prediction.

However, they cannot reveal anything about the abstract approach to business. No strategy can be revealed. If a company or organization pivots and changes direction, none of this information can be obtained from alternative data sources.

However, they can reveal the effectiveness of these pivots or changes. As such, alternative data can provide valuable information about a company’s expected short-term performance, but not much more.

We have some evidence that financial services organizations have begun to use alternative data by at least similar means. A survey by Censuswide and Oxylabs has shown that financial services organizations rank web scraping, an alternative method of data acquisition, as one of the most impactful in terms of revenue generation.

Related: The Top 4 Cash Flow Forecasting Mistakes

Alternative data has a lot of buzz around. There are good reasons to be excited, especially if you are involved in the financial sector. It is a completely new source of data that can provide an advantage over the competition.

However, I would like to warn you that it does not go into any of them. Alternative data is surprisingly good, by its nature, for providing signals that show short-term performance. It is the very nature that prevents it from being as useful or useful in long-term performance predictions.

In the end, most alternative data hides signals about short-term performance. As such, it should be used only for this purpose. Trying to apply longer-term signals, such as five-year forecasts, can even be detrimental.

Finally, alternative data should also be weighted with opportunity cost. Removing the signals requires more work than with traditional datasets. Working with alternative data means subtracting resources from other potential strategies.

Source link

Leave a Comment