scholarly journals Mutual Fund Rating Prediction using Proportional Odds Logistic Regression with Imbalanced Class

Mutual funds ratings given by rating agencies, are very popular and helps new/first time investors to select and invest in funds based on the ratings a fund takes without going through the detailed portfolio. However sometimes these ratings could be biased or incorrect or in favor of specific fund and it could affect an investor decision. New investors face a lot of problems while investingand choosing mutual funds due to poor professional advice and lack of right tools and resources to assess a funds true performance. To overcome the problem of incorrect rating and to help an investor to choose the funds wisely using machine learning, we have attempted to predict the rating and classify mutual funds using proportional odds logistic regression which classifies funds intorating classes from 1 to 5 with 5 being the high rated fund and 1 being the low rated fund. While some prior studies have suggested methods of using clustering to classify based on performances using Supervised/Unsupervised learning, this paper deals with supervised learning forpredicting the ratings using the mutual fund financial ratios and also handles imbalanced classes.To handle imbalance class problem in a multi-class setting, we propose a new class balancing hybrid methodology of using EM and Gauss-Smote sampling that significantly improves the rating prediction

2013 ◽  
Vol 1 (1) ◽  
pp. 163-170
Author(s):  
Prathap G ◽  
Rajamohan A

Among various financial instruments, i.e., shares, bonds and debentures. Mutual Fund is a special type of financial instrument that pools the funds of investors who seek to maximize return on investment. Stocks provide high total returns with commensurate level of risk, while bonds may provide lower risks along with regular income. Small investors face a lot of problems in the share market, limited resources, lack of professional advice, lack of information etc. Mutual funds have come as a much needed help to these investors. It is a special type of institutional device or an investment vehicle through which the investors pool their savings which are to be invested under the guidance of a team of experts in wide variety of portfolios of corporate securities in such a way, so as to minimize risk, while ensuring safety and steady return on investment.


2020 ◽  
pp. 40-60
Author(s):  
T. V. Teplova ◽  
T. V. Sokolova ◽  
A. Fasano ◽  
V. A. Rodina

In our paper, we study the impact of active investment strategies and factors of their success in the Russian market of collective investment — self-confidence of managers, commissions of management companies (MC) — on return rates of mutual funds. For the first time, not only equity mutual funds, but also bond mutual funds are considered as an object of study; the time period is since 2012. Our study is based on data on the structure of mutual fund portfolios provided by Investfunds. We propose a number of original indicators of an active management style and consider the profitability of mutual funds relative to various benchmarks. Based on testing of multivariate regression models, it has been revealed that the return rate of equity mutual funds is negatively affected by a share of stocks in the fund portfolio which are not included in the market index. When managers take into account their previous negative investment experience, it contributes to the growth of mutual fund return rates. Active investment strategies correlate with increased commissions (up to 4.5% of NAV), but they do not allow an investor to receive higher return rates than index investments. An increase in the share of corporate bonds allows the fund manager to outperform benchmarks for bond funds. For the first time, a nonlinear relationship between the size of mutual funds and the value of commissions has been revealed for the Russian market.


2018 ◽  
Vol 35 (1) ◽  
pp. 137-152 ◽  
Author(s):  
Andreas Oehler ◽  
Andreas Höfer ◽  
Matthias Horn ◽  
Stefan Wendt

Purpose Retail investors use information provided by mutual fund rating agencies to make investment decisions. This paper aims to examine whether the ratings provide useful information to retail investors by analyzing the rating migration and closure risk of mutual funds that received Morningstar’s mutual fund ratings from 2005 to 2012. Design/methodology/approach The research design differentiates between buy-and-hold investment strategies and dynamic investment strategies. To assess the information content of mutual fund ratings for buy-and-hold investment strategies, the rating migration based on the first and the last mutual fund rating during two-, four-, six- and eight-year horizons is determined. With respect to dynamic investment strategies, the number of rating changes per fund on a monthly basis during these time horizons is calculated. Findings Mutual fund rating persistence is low or even inexistent, in particular, during longer time periods. Only for lower-rated funds, the rating appears to indicate higher risk of fund closure. In addition, mutual funds face a large number of up to 38 monthly rating changes in the eight-year window. Originality/value Mutual fund rating persistence has hardly been analyzed for funds offered to retail investors so far. This paper clearly points out that because of the extensive rating migration and the high number of monthly rating changes, retail investors barely benefit from using mutual fund ratings.


2019 ◽  
Vol 54 (5) ◽  
pp. 58
Author(s):  
Preeta Sinha ◽  
Tamal Taru Roy ◽  
Debi Prasad Lahiri
Keyword(s):  

2019 ◽  
Vol 118 (8) ◽  
pp. 28-34
Author(s):  
Dr. V. Murali Krishna ◽  
Dr T. Hima Bindu ◽  
Dr. Ravikumar Gunakala

Mutual Fund Industry is one of the emerged dominant financial intermediaries in Indian Capital Market. The main objective of investing in a mutual fund is to diversify risk. Though the mutual fund invests in diversified portfolio, the fund managers take different levels of risk in order to achieve the schemes objectives. Mutual funds allow portfolio diversification and relative risk management through collection of funds from the savers/investors, the same investing in equity and debt stocks. This type of invested funds is managed by professional experts called as fund managers Funds are categorized as income should fixed base in India are a kind of mutual fund which makes investment in debt securities that have been issued to the corporate, banking institutions and to government in general


2016 ◽  
Vol 5 (2) ◽  
Author(s):  
Ratish C Gupta ◽  
Dr. Manish Mittal

The Indian mutual fund industry is one of the fastest growing and most competitive segments of the financial sector. The extent of under-penetration in the market is a sore point with the financial services industry, with a large amount of savings being channelized into fixed deposits, gold and real estate rather than the capital markets. The mutual fund industry is yet to spread its reach beyond Tier I cities. The top fifteen cities contribute to 85% of the pie, with the remaining 15% distributed among other cities. The study seeks to determine the impact of decision making of investors on current situation of mutual fund industry.


Author(s):  
Ram Pratap Sinha

Performance analysis of mutual funds is usually made on the basis of return-risk framework. Traditionally, excess return (over risk-free rate) to risk ratios were used for the purpose mutual fund evaluation. Subsequently, the application of non-parametric mathematical programming techniques in the context of performance evaluation facilitated multi-criteria decision making. However,the estimates of performance on the basis of conventional programming techniques like DEA and FDH are affected by the presence of outliers in the sample observations. The present, accordingly uses more robust benchmarking techniques for evaluating the performance od sectoral mutual fund schemes based on observations for the second half of 2010. The USP of the present study is that it uses two partial frontier techniques (Order-m and Order- a) which are less susceptible to the problem of extreme data.


2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Mark A. T. Blaskovich ◽  
Angela M. Kavanagh ◽  
Alysha G. Elliott ◽  
Bing Zhang ◽  
Soumya Ramu ◽  
...  

AbstractAntimicrobial resistance threatens the viability of modern medicine, which is largely dependent on the successful prevention and treatment of bacterial infections. Unfortunately, there are few new therapeutics in the clinical pipeline, particularly for Gram-negative bacteria. We now present a detailed evaluation of the antimicrobial activity of cannabidiol, the main non-psychoactive component of cannabis. We confirm previous reports of Gram-positive activity and expand the breadth of pathogens tested, including highly resistant Staphylococcus aureus, Streptococcus pneumoniae, and Clostridioides difficile. Our results demonstrate that cannabidiol has excellent activity against biofilms, little propensity to induce resistance, and topical in vivo efficacy. Multiple mode-of-action studies point to membrane disruption as cannabidiol’s primary mechanism. More importantly, we now report for the first time that cannabidiol can selectively kill a subset of Gram-negative bacteria that includes the ‘urgent threat’ pathogen Neisseria gonorrhoeae. Structure-activity relationship studies demonstrate the potential to advance cannabidiol analogs as a much-needed new class of antibiotics.


Sign in / Sign up

Export Citation Format

Share Document