Syeda Farheen Akhtar

Academic

Career

Verbatim text

Al-Driven Portfolio Optimization: 
A Comparative Analysis using Artificial Intelligence and Traditional 
Models 
This research investigates the optimization of stock investment portfolios using both Al-driven and 
traditional methods. The study compares Al techniques such as Genetic Algorithms and 
Reinforcement Learning with traditional Modern Portfolio Theory to determine which approach 
yields superior risk-adjusted returns. Using historical data from the top 100 stocks in China and 
Pakistan, the study aims to identify the strengths and limitations of both methods. Additionally, the 
research explores how these approaches can contribute to achieving the United Nations 
Sustainable Development Goals (SDGs), particularly in the areas of economic growth, responsible 
consumption, and financial innovation. The findings will offer valuable insights into enhancing 
portfolio optimization and investment strategies, helping investors and financial analysts make 
more informed decisions. 
Key Words: Portfolio Optimization, Artificial Intelligence, Genetic Algorithms, Reinforcement Learning, 
Modern Portfolio Theory 
Al-DRIVEN PORTFOLIO 
OPTIMIZATION 
A Comparative Analysis using 
Artificial Intelligence and Traditional Models 
OBJECTIVE 
Evaluate the effectiveness of Al techniques, 
specifically Genetic Algorithms and 
Reinforcement Learning, 
alongside traditional Modern Portfolio Theory 
to determine which approach yields superior 
risk-adjusted returns. 
Area of Study: 
Finance 
Supervisor Name: 
Dr. Muhammad Yasir 
Group Members: 
Areeba Tariq (i21 - 1401) 
Zoya Akbar (i21- 1403) 
Ayesha Siddiqa (i21 - 1422) 
Syeda Farheen Akhtar (i21 - 2602)