Abstract:

This study analyses the influence of quarterly board room discussions conducted in the form of “Earnings Call Transcripts” and company’s stock price changes in the subsequent periods. In this study, sentiments were extracted from the “textual quarterly transcripts” of three major software companies for the last ten years. The extracted sentiments were statistically analyzed for patterns and types. The study led to the development of a new response variable called the ‘Inverse Effect’. The ‘Inverse Effect’ simply refers to the discordance between the sentiment in the boardroom discussions available in the document form and changes in the stock price movements. If the sentiment for the current quarter is positive and the changes in the stock price movements is also positive in the subsequent quarter, it is considered as “concordance” and if the changes in the stock price movements is opposite to the sentiments it will be called as “discordance” which is the inverse effect. The study basically looks at the areas where the Weak Market Hypothesis (WMH) is not valid. The findings emerged from the study suggest a possible causality between the sentiments in the transcripts and the stock price changes. It was also found that sentiment polarity, threequarter average stock price and the previous quarter stock price are the key determinants of the ‘Inverse Effect’. Based on the findings from the study, appropriate machine learning models were developed and evaluated to predict the ‘Inverse Effect’ on the performance of individual stocks of a few select companies.

Keywords— Efficient Market Hypothesis, Weak Market Hypothesis, Earnings Call Transcripts, Lexicon Based Sentiments Analysis, Polarity, Earnings per Share, Market Performance, Stock Price, ‘Inverse Effect’, Behavioral Finance.

Conference Name: International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

Published in: Deploying NLP Techniques for Earnings Call Transcripts for Financial Analysis: A Reverse Phenomenon Paradigm | IEEE Conference Publication | IEEE Xplore