Vinod Gupta School of Management, IIT Kharagpur

Corporate Finance Assignment

Submitted To:
A. K. Mishra

Submitted By:
Mohika Agrawal – 23BM63087
Abstract
The report presents the application of linear programming methods, particularly the simplex
method with the intend of allocating funds in the stock market for maximizing returns. By
systematically distributing funds across various stocks, considering factors like budget, risk
tolerance, and diversification, linear programming offers an effective solution to optimize
investment decisions. The report highlights how this helps investors in achieving the highest
possible returns within specified constraints, providing a systematic approach to navigate the
complexities of the dynamic stock market environment.

Introduction
The Stock Exchange Investment problem poses a fundamental challenge in finance—how to
strategically invest a predefined sum in the stock market to maximize returns. This report
investigates the application of the simplex method, a powerful tool in linear programming, to
address this optimization dilemma. The objective is clear that is finding the most effective
allocation of funds across diverse stocks, all while navigating constraints like budget limitations,
risk tolerance, and the imperative of portfolio diversification.

The report aims to demonstrate the practical utility of the simplex method in solving the Stock
Exchange Investment problem, showcasing how this mathematical approach facilitates informed
decision-making in the face of the dynamic and intricate stock market landscape. This breaks
down the process, making it easier to understand how linear programming can help in navigating
the dynamic world of stock investments.

Methodology
The objective is to find the optimal allocation of money among five stocks (Apple, Microsoft,
Amazon, Tesla, and Netflix) that maximizes the expected return while satisfying the constraints
on budget, risk, and diversification.

Assumptions
- Expected Return and Risk Equivalence: For simplicity, we assume that the annualized returns
and standard deviations provided for each stock represent the expected return rates and risk
levels, respectively.
- Diversification Limit: A diversification limit is set to restrict the investment in any single stock
to 40% of the total budget.

Mathematical Model
The linear programming problem for stock exchange investment is as follows:

Let xi be the amount of money invested in stock i, where i=1,2,3,4,5 corresponds to Apple,
Microsoft, Amazon, Tesla, and Netflix, respectively.
Data:
The annualized returns of the stocks are based on the data from as of April 9, 2023.

Stock Annualized Returns (%) Standard Deviation (%)

Apple 22.54 25.67
Microsoft 28.32 21.45
Amazon 18.76 23.12
Tesla 41.23 48.36
Netflix 24.65 27.89

Objective function:
The objective function is the expected return from the investment, which is the sum of the
products of the decision variables and the annualized returns of the corresponding stocks. It
represents the goal of the investor, which is to maximize the profit from the investment.

5
Max ∑ x i r i
i=1

where ri is the annualized return of stock i.

Subject to Constraints:
 Budget constraint:
Total amount of money invested should be less than the available budget of $10000. This
ensures that the investor spends equal to the budget.
5

∑ x i≤10000
i=1

 Risk constraint:
Total risk level of the portfolio should not exceed 5% of available budget. The risk level
of the portfolio is the sum of the products of the decision variables and the standard
deviations of the corresponding stocks. The standard deviation of a stock measures the
volatility or the uncertainty of its return. A higher standard deviation means a higher risk,
and vice versa. It ensures that the investor does not take too much risk with the
investment.
5

∑ x i s i /100≤500
i=1

where si is the standard deviation of stock i.

 Diversification constraint:
Portfolio should be diversified, meaning that no more than 20% of the money should be
invested in any single stock. This ensures that the investor does not put all the eggs in one
 basket, and reduces the exposure to the specific risk of each stock. Diversification can
help reduce the overall risk of the portfolio and increase the chance of getting a positive
return.

x i ≤ 0.2 ×1000 ∀ i=1 ,2 , ... ,5

 Non-negativity constraint:
Decision variables should be non-negative. This ensures that the investor does not sell or
short any stock, and only invests in positive amounts of each stock.

x i ≥ 0 ∀ i=1 ,2 , ... ,5

The chosen solution technique is simplex method which is a mathematical tool used for solving
linear programming problems. It's an iterative approach that navigates through feasible solutions
within a defined constraint space to optimize an objective function. By moving from one feasible
solution to another, the simplex method systematically identifies the best solution that maximizes
or minimizes the objective function under the given constraints.
In this scenario, the simplex method is applied to maximize returns on investment under above
mentioned constraints.

Solving Using AMPL

AMPL (A Mathematical Programming Language) is a tool used to solve optimization problems
by describing mathematical models in a structured and easy-to-understand way. To use AMPL,
you input the decision variables, constraints, and objective function, the software then applies
mathematical techniques like the simplex method to find the best solution that satisfies the given
conditions. By utilizing AMPL's syntax and connecting it with a compatible solver, we can
efficiently find the optimal investment strategy while considering budget, risk, and
diversification constraints.

AMPL Code File:

File name: Maximize_Returns.mod
var x1; #Apple
var x2; #Microsoft
var x3; #Amazon
var x4; #Tesla
var x5; #Netflix
maximize Returns: (x1 * 22.54 + x2 * 28.32 + x3 * 18.76 + x4 * 41.23 + x5 * 24.65)/100;
#Objective function maximize returns of investment
subject to Budget_Constraint: x1 + x2 + x3 + x4 + x5 <= 10000;
subject to Risk_Constraint: (x1 * 25.67 + x2 * 21.45 + x3 * 23.12 + x4 * 48.36 + x5 * 27.89) /
100 <= 500;
subject to Diversification_Constraint1: x1 <= 2000;
subject to Diversification_Constraint2: x2 <= 2000;
subject to Diversification_Constraint3: x3 <= 2000;
subject to Diversification_Constraint4: x4 <= 2000;
subject to Diversification_Constraint5: x5 <= 2000;
subject to Non_negativity_Constraint1: x1 >= 0;
subject to Non_negativity_Constraint2: x2 >= 0;
subject to Non_negativity_Constraint3: x3 >= 0;
subject to Non_negativity_Constraint4: x4 >= 0;
subject to Non_negativity_Constraint5: x5 >= 0;

Results and Discussions

The optimized investment strategy, derived from the linear programming model, allocates funds
judiciously across Apple, Microsoft, Tesla, and Netflix while adhering to budget, risk, and
diversification constraints. Key findings reveal a balanced risk-return tradeoff, effective
diversification, and full budget utilization. The model provides valuable insights for strategic
decision-making, emphasizing its real-world applicability and sensitivity to market dynamics.

Conclusion
The optimized investment allocation derived from the linear programming model indicates a
promising strategy for maximizing returns within budget, risk, and diversification constraints.
The results underscore the efficacy of mathematical tools, particularly the simplex method, in
making informed investment decisions. Future prospects lie in the model's adaptability to real-
time market changes and its potential for dynamic portfolio management. However, the model's
assumptions and exclusions—like the stability of stock characteristics and the absence of
transaction costs—highlight areas for refinement to enhance its practical applicability and foster
more robust outcomes in the dynamic landscape of stock exchange investment.

Bibliography
https://www.investopedia.com/articles/basics/03/050203.asp