Descriptive Analytics for Text Data

Problem

  • An earnings call is a conference call between the management of a public company, analysts, investors, and the media to discuss the company's financial results during a given reporting period, such as a quarter or a fiscal year.
  • The objective here is to analyze the quarterly earnings conference call transcripts of different companies, with the help of NLP, and to identify the new themes, opportunities and risks that company management is sharing with the investors.

Solution

  • Fetched the earning call data and the stock price data of 10 different companies
  • The frequency of positive, negative, uncertain, litigious and constraining words are analyzed for each quarter, which helped to understand how well the company is performing
  • The stock price data was also compared with the sentiments, and a correlation was found, where the stock prices were seen decreasing when the negative words increased
  • Also, the most frequently occurring words in each call was analyzed

Impact

01

Analysis of earning calls will help to understand about the performance of the company. For example, if the number of negative words in a call are very high, we can say that there are lot of issues within the organization

02

The analysis helps to compare the performance and stock prices between different companies. This will help to identify the potential competitors. The sentiment analysis will help understand why the company is lagging or leading with respect to others

03

Since we are mapping the performance into plots, any person like stakeholders, investors, employees, costumers, etc. will easily understand the overall performance of the company

Scroll to Top