Outbreak and spread of the Covid-19 pandemic have touched to the core of our sentiments. Indian stock market has seen a roller coaster ride so far this year amid the Covid-19 pandemic. Sentiments have turned out to be a significant influence on the movement of the Indian stock market and pandemic has only added more steam. This study with the limelight on the Covid-19 pandemic is an endeavour to investigate the classification accuracy of selected ML algorithms under natural language processing for sentiment analysis and prediction for the Indian stock market. The study proposes the framework for sentiment analysis and prediction for the Indian stock market where six ML algorithms are put to test. Consequently, the study highlights the superior algorithms based on accuracy results. These superior algorithms can be potent input to build robust prediction models as a logical next step.

Turn of the month (TOM) is a widely recognized anomaly and studied majorly in the context with equity markets. However, the global mutual fund market has not been much exposed to empirical testing of the TOM anomaly and the implication thereof. This study has dual objectives of not only investigating if the TOM effect persists in the world of equity mutual funds but also proposing an investment strategy to exploit the TOM anomaly to mutual fund investors. The study examines 40 equity mutual funds across 6 different geographies and 2 multi-geographic segments. For the sample period of 15 years (2005–2020), crucially covering financial crisis as well as an outbreak of the Covid-19 pandemic this study confirms a statistically significant effect of TOM for 23 out of 40 funds. Based on findings, the paper proposes a staggered investment strategy to investors in mutual funds for entry and exit to exploit the TOM effect for return enhancement.

No abstract

No abstract

No abstract