0% found this document useful (0 votes)
9 views10 pages

Markov Chain Analysis of Auto Market Share

Uploaded by

omc.msdsm01
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
9 views10 pages

Markov Chain Analysis of Auto Market Share

Uploaded by

omc.msdsm01
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

This project employs a Markov Chain model to analyze market share dynamics in the auto industry, focusing on six

This
project employs a Markov Chain model to analyze market share dynamics in
the auto industry, focusing on six major brands—Maruti, Hyundai, Mahindra,
Tata, Toyota, and Honda. Through a simulation spanning short-term transitions
and long-term steady-state probabilities, the study uncovers insights valuable
to stakeholders in the automotive sector. The short-term analysis highlights
brand-specific sensitivities to market changes, while the long-term predictions
offer a stable equilibrium perspective. Maruti emerges as a consistent market
leader, and the findings provide actionable intelligence for investors,
policymakers, and industry leaders. Despite model simplifications, the study
opens avenues for future research, emphasizing the need for collaboration
with industry experts and continuous refinement for enhanced predictive
accuracy and real-world applicability. Overall, this project serves as a
foundational exploration into market share analysis, paving the way for more
nuanced investigations within the dynamic auto industry landscape.

Market Share in Auto Industry

ADITYA SINHA 2023DSS1001


SOURIT KHAMARU 2023DSS1034
PRIYAMJEET KUMAR 2023DSS1025
OM CHOUHAN 2023DSS1022
Introduction

The aim of this project is to analyze the market shares of major automotive brands—Maruti,

Hyundai, Mahindra, Tata, Toyota, and Honda—over time using a Markov Chain model. The

Markov Chain will simulate the transition of market shares among these brands, and we will

explore both the short-term transitions and the long-term steady-state probabilities.

Methodology

1. Transition Matrix

The transition matrix represents the probabilities of transitioning from one state (market share

of a brand) to another in a single time step. The provided transition matrix is as follows:

[
[0.9, 0.05, 0.02, 0.02, 0.005, 0.005],
[0.03, 0.85, 0.05, 0.03, 0.02, 0.02],
[0.01, 0.02, 0.9, 0.03, 0.02, 0.02],
[0.008, 0.01, 0.02, 0.9, 0.04, 0.02],
[0.005, 0.005, 0.01, 0.03, 0.9, 0.03],
[0.004, 0.004, 0.008, 0.01, 0.05, 0.925]
]

2. Initial State

The initial state represents the market shares of each brand at the starting point. The provided

initial state is:

[30%, 20%, 15%, 10%, 8%, 7%]


3. Markov Chain Simulation

We simulated the Markov Chain over a specified number of steps (in this case, 5 steps). Each

step represents a time unit, and the market shares of each brand evolve based on the transition

probabilities.

4. Visualization

The market shares over time were visualized using a line plot, where each brand is

represented by a different line. Brand names (Maruti, Hyundai, Mahindra, Tata, Toyota,

Honda) were included for clarity.

Results

1. Market Share Transition Over Time

The plotted graph illustrates the evolution of market shares for each brand over the simulated

time period. This visualization provides insights into the dynamics of market share changes.
2. Steady-State Probabilities

Steady-state probabilities represent the long-term distribution of market shares, assuming the

Markov Chain reaches a stable state. The steady-state probabilities were calculated using the

eigenvector corresponding to the eigenvalue of 1.

The steady-state probabilities are as follows:

 Maruti: 0.3000

 Hyundai: 0.1998

 Mahindra: 0.1482

 Tata: 0.0997

 Toyota: 0.0796

 Honda: 0.0727
Conclusion

The analysis of market share dynamics in the auto industry using the Markov Chain model

provides several key insights into the behavior of major brands—Maruti, Hyundai, Mahindra,

Tata, Toyota, and Honda. The detailed examination of the results allows us to draw nuanced

conclusions about short-term transitions and long-term steady-state probabilities.

Short-Term Transitions

The simulated Markov Chain reveals the short-term fluctuations in market shares over the 5-

step period. Brands exhibit varying degrees of sensitivity to market dynamics, with some

experiencing rapid changes while others demonstrate more stability. This information is

crucial for understanding the immediate impact of external factors on each brand's market

position.

For instance, during the short-term simulation, Maruti consistently maintains a dominant

position, reflecting a high transition probability of staying in the leading position. On the

other hand, brands like Tata and Honda show more variability in their market shares,

indicating a higher likelihood of experiencing fluctuations in the short term.

Long-Term Steady-State Probabilities

The calculation of steady-state probabilities offers a glimpse into the equilibrium that the

market shares may reach in the long run. These probabilities represent the relative

proportions of market shares that each brand is expected to hold over an extended period,

assuming a stable market environment.

In the long-term, the analysis suggests that Maruti is likely to maintain its leadership position

with a steady-state probability of 30.00%. Hyundai follows closely with a probability of

19.98%, emphasizing its sustained competitiveness. Mahindra, Tata, Toyota, and Honda
secure positions in the market with probabilities of 14.82%, 9.97%, 7.96%, and 7.27%,

respectively.

Implications for Stakeholders

Stakeholders in the auto industry, including investors, policymakers, and company

executives, can use these insights to make informed decisions. Understanding both short-term

volatility and long-term stability is crucial for strategic planning, resource allocation, and risk

management.

For instance, Maruti's consistently high probability of maintaining a significant market share

signals its resilience, making it an attractive investment option. On the other hand, brands

with higher short-term variability may need to focus on adaptive strategies to navigate

fluctuations effectively.

Limitations and Future Directions

It's important to note that the Markov Chain model simplifies the complex dynamics of the

auto industry, and real-world factors such as consumer preferences, economic conditions, and

technological advancements are not fully captured. Future iterations of this analysis could

incorporate more granular data, consider external influences, and employ advanced modeling

techniques for a more accurate representation.

Collaboration with industry experts and continuous refinement of the model based on real-

world data can enhance its predictive power and practical applicability. Additionally,

expanding the analysis to include regional variations, emerging markets, and specific product

categories could provide a more comprehensive understanding of market dynamics.

In conclusion, this project serves as a foundational exploration into the use of Markov Chains

for market share analysis, offering valuable insights into both short-term trends and long-term
stability. It lays the groundwork for further research and strategic decision-making within the

dynamic landscape of the auto industry.

References

1. Norvig, P., & Russell, S. (2010). Artificial Intelligence: A Modern Approach. Prentice

Hall.

2. Stewart, W. J. (2009). Probability, Markov Chains, Queues, and Simulation: The

Mathematical Basis of Performance Modeling. Princeton University Press.

3. Python documentation for NumPy and SciPy: NumPy, SciPy.

4. Industry reports, financial statements, and market research publications for obtaining
market share data.
Python Code:
import numpy as np

import [Link] as plt

# Transition matrix

transition_matrix = [Link]([

[0.9, 0.05, 0.02, 0.02, 0.005, 0.005],

[0.03, 0.85, 0.05, 0.03, 0.02, 0.02],

[0.01, 0.02, 0.9, 0.03, 0.02, 0.02],

[0.008, 0.01, 0.02, 0.9, 0.04, 0.02],

[0.005, 0.005, 0.01, 0.03, 0.9, 0.03],

[0.004, 0.004, 0.008, 0.01, 0.05, 0.925]

])

# Initial state

initial_state = [Link]([30, 20, 15, 10, 8, 7]) / 100 # Convert percentages to fractions

# Simulate the Markov Chain

num_steps = 5

brand_names = ['Maruti', 'Hyundai', 'Mahindra', 'Tata', 'Toyota', 'Honda']


market_shares_over_time = [initial_state]

for _ in range(num_steps):

next_state = [Link](initial_state, transition_matrix)

market_shares_over_time.append(next_state)

initial_state = next_state

# Plotting market shares over time

market_shares_array = [Link](market_shares_over_time).T

[Link](figsize=(10, 6))

for i in range(len(market_shares_array)):

[Link](range(num_steps + 1), market_shares_array[i], label=brand_names[i])

[Link]('Year')

[Link]('Market Share')

[Link]('Markov Chain: Market Share Transition Over Time')

[Link]()

[Link](True)

[Link]()
# Calculate the steady-state probabilities

eigenvalues, eigenvectors = [Link](transition_matrix.T)

steady_state_probabilities = [Link](eigenvectors[:, 0] / eigenvectors[:, 0].sum())

# Display steady-state probabilities

print("\nSteady-State Probabilities:")

for i, prob in enumerate(steady_state_probabilities):

print(f'{brand_names[i]}: {prob:.4f}')

You might also like