disadvantages, while the group decision-making
strategy can effectively integrate the strengths of
multiple algorithms and reduce the limitations of a
single algorithm. The newly developed
comprehensive algorithm outperforms the benchmark
index in terms of fund curve performance and is
slightly superior to the other three individual
algorithms. Its key performance indicators include: a
standard deviation of 1.2695, a Sharpe ratio of
0.3991, an information ratio of 0.6622, a maximum
drawdown of 35.45%, and an algorithm accuracy rate
of 54.19%. Although the new algorithm demonstrates
advantages in terms of return, its higher standard
deviation and maximum drawdown indicate that the
algorithm tends to adopt a conservative strategy in
stock selection, resulting in a smaller number of
selected stocks and a higher degree of investment
concentration, thereby failing to fully diversify risks.
Therefore, a comprehensive assessment of the new
algorithm's overall capabilities requires further
validation based on a larger stock pool and data
spanning a longer time period. Overall, each
algorithm can outperform the benchmark index to a
certain extent, achieving excess returns. However,
while pursuing high returns, it is often difficult to
effectively control risk indicators such as variance
and maximum drawdown. In practical operations, the
introduction of risk management measures such as
stop-loss orders can help control the overall risk of
the portfolio. There is still room for optimization in
this study: firstly, transaction costs, both explicit and
implicit, are not considered; secondly, machine
learning algorithms are constantly evolving, and more
cutting-edge algorithms can be explored in the future;
thirdly, the handling of missing data during the data
cleaning process needs improvement. For individual
investors, this paper recommends adopting a
contrarian investment strategy, avoiding chasing
gains and cutting losses, holding undervalued stocks
for the long term, and focusing on portfolio
diversification to reduce risks and transaction costs.
For institutional investors, this paper encourages
them to pay more attention to key indicators such as
stock valuation, company development, and
profitability in quantitative investment to achieve
higher returns and guide the market towards a more
efficient direction. Additionally, future research
should further validate the performance of this
strategy in real markets and continuously optimize
algorithms and data processing methods.
REFERENCES
Ahlem, L., Ahmed, J., Tarek, F., 2024. Spillovers between
cryptocurrencies, gold and stock markets: implication
for hedging strategies and portfolio diversification
under the COVID-19 pandemic. Journal of Economics,
Finance and Administrative Science, 57, 21-41.
Alexey, R., Sally, S., 2024. Dynamic portfolio decisions
with climate risk and model uncertainty. Journal of
Sustainable Finance, Investment, 2, 344-365.
Brito, I., 2023. A portfolio stock selection model based on
expected utility, entropy and variance. Expert Systems
With Applications, 1, 12-14.
Burkart, F. W., Roberto, B. J., 2023. Random walk through
a stock network and predictive analysis for portfolio
optimization. Expert Systems With Applications, 14,
45-47.
Claudiu, V., Marcel, A., 2023. Portfolio Volatility
Estimation Relative to Stock Market Cross-Sectional
Intrinsic Entropy. Journal of Risk and Financial
Management, 2, 114-114.
Dejan, Z, Slavica, M., Jasmina, D, Gajić-Glamočlija,
Marina, 2022. Oil hedging with a multivariate
semiparametric value-at-risk portfolio. Borsa Istanbul
Review, 6, 1118-1131.
Dejan, Z., Biljana, P., Nataša, P., et al., 2023. How to reduce
the extreme risk of losses in corn and soybean markets?
Construction of a portfolio with European stock
indices. Agricultural Economics, Zemědělská
ekonomika, 3, 109-118.
Francois, P., Richard, A., Lorraine, M., Tinotenda, M. H.,
2023. The Impact of Investor Sentiment on Housing
Prices and the Property Stock Index Volatility in South
Africa. Real Estate Management and Valuation, 2, 1-
17.
He, P., Hu, K., Nie, S., et al., 2023. Stock Selection and
Portfolio Performance Based on ESG Scores.
Academic Journal of Business, Management, 11.
Kinda, D., Sulaiman, M., 2023. Portfolio Optimization at
Damascus Securities Exchange: A Fractal Analysis
Approach. Cogent Economics, Finance, 2, 82-84.
Kirti, S., Kumar, A., Prachi, P., Purohit, H., 2023. Did ESG
portfolio augment investors’ wealth during Covid19?
Evidence from Indian stock market. Sustainability
Accounting, Management and Policy Journal ,5,, 922-
944.
Lean, H., Pizzutilo, F., Kimberly, G., 2023. Portfolio
performance implications of investment in renewable
energy equities: Green versus gray. Corporate Social
Responsibility and Environmental Management, 6,
2990-3005.
Liu, X., Shehzad, K., Kocak, E., Zaman, U., 2022. Dynamic
correlations and portfolio implications across stock
and commodity markets before and during the COVID-
19 era: A key role of gold. Resources Policy 102985-
102985.
Palma, M. M., Eva, L. M., Pavel, A., et al, 2023. Stock
selection using a multiple criteria hierarchical process
in the Dow Jones index. International Journal of
Innovation and Sustainable Development, 1-2, 67-84.