In recent decades, the field of Computer Science has increasingly infiltrated the realms of finance and economics. Leading financial institutions are depending on computers to yield results. For instance, JP Morgan, Chase, and Barclays utilize supercomputers to assess the risk of a stock portfolio and forecast the future value of an asset. How do they accomplish this?

This article will delve into how computers interpret sentiment and apply machine learning to enhance investment returns.

Sentiment Analysis

The market dynamics have transitioned from investing based on gut feelings to placing confidence in computer programs. The era of traders hurriedly buying and selling stocks on the trading floor is diminishing. In their place are quantitative analysts, often referred to as quants. Quants design computer algorithms with a strong focus on mathematics to carry out trades and predict a stock’s future performance.

Recognizing the evolving market landscape, Dow Jones has established a lexicon that enables computers to effectively analyze potential stock movements. Another term for lexicon is dictionary. The Dow Jones Lexicon (DJL) compiles financial news and translates it into a language comprehensible by computers. Additionally, the DJL comprises six distinct dictionaries, all crafted by Bill McDonald, a finance professor at the University of Notre Dame. Nonetheless, financial institutions have the option to develop their own dictionaries tailored to their unique requirements.

When a computer is equipped with a lexicon, it can differentiate between positive and negative news. This knowledge subsequently assists traders in determining whether executing a trade for that stock would be advantageous.

The graphic below illustrates whether the sentiment surrounding a stock is bullish (positive) or bearish (negative).

Let’s investigate a news article to see how the sentiment lexicon functions. This article originates from CNBC and was published on November 26, 2021, just days following the discovery of a new COVID variant by scientists in South Africa.

This is the introductory sentence of the article. You’ll observe that one of the first words is “dropped.” A computer analyzing this snippet of text would categorize it in the negative section, lowering the sentiment score and suggesting that the stock market is bearish. Additionally, the positioning of the word is crucial. Keywords found in headlines or the initial lines carry more significance in the sentiment score than those buried deep within the text.

In this screenshot, you’ll spot keywords like “down,” “dropped,” “lost,” and “fell.” These words will be interpreted by the computer as negative, thus reducing the sentiment score.

So, what does this look like from the computer’s standpoint? The process turns out to be relatively straightforward. Developing a sentiment analysis program is accomplished through XML code. XML, or extensible markup language, is closely related to HTML but is not an independent language. HTML specifies how a document should appear, while XML defines the data contained within the document. For example, in HTML, there are tags that programmers use to create specific objects, such as the

tag which denotes the main heading of a website (h for heading; 1 for the primary heading). In contrast, XML permits programmers to further customize their code. Instead of utilizing a broadly defined

tag, XML allows for more specific tags like to clarify what is being defined. This enhances code interpretability and aligns it with a business’s requirements.

Note: the code below was compiled by sqlauthority.com

   White

   Blue

   Black

   Green

   Red