KARNATAK LAW SOCIETY’S

GOGTE INSTITUTE OF TECHNOLOGY

UDYAMBAG, BELAGAVI-590008

(An Autonomous Institution under Visvesvaraya Technological University, Belagavi)

(APPROVED BY AICTE, NEW DELHI)

Department of Mathematics

A Course Seminar Report on

“TIME SERIES ANALYSIS”

Name USN Signature

P.G Ambica Sony 2GI21IS041

Shivani Uday Raikar 2GI21ME082

Tanisha Hattarki 2GI21EC155

Varsha Kannur 2GI21CS186

Under the guidance of

Prof. Vani V Deshpande
 KARNATAK LAW SOCIETY’S

GOGTE INSTITUTE OF TECHNOLOGY

UDYAMBAG, BELAGAVI-590008
(An Autonomous Institution under Visvesvaraya Technological University,
Belagavi)
(APPROVED BY AICTE, NEW DELHI)
Department of Information Science & Engineering

Certificate
This is to certify that the Course Activity titled “TIME SERIES ANALYSIS” carried out by
students P.G Ambica Sony [2GI21IS041], Shivani Uday Raikar [2GI21ME082], Tanisha
Hattarki [2GI21EC155], Varsha Kannur [2GI21CS186] is submitted in partial fulfilment of
the requirements for 7th semester B.E. for Maths, Vishveshvaraya Technological University,
Belagavi. It is certified that all corrections/suggestions indicated have been incorporated in the
report. The course project report has been approved as it satisfies the academic requirements
prescribed for the said degree.

Date: Signature of Guide

Place: Belagavi Prof. Vani V

Deshpande
INDEX
SL NO. CONTENTS Page no.

1. ABSTRACT 2

2. INTRODUCTION 2

3. KEY CONCEPTS IN TIME SERIES ANALYSIS 3

4. TIME SERIES PLOTS 4

5. TIME SERIES MODELS 5

6. APPLICATIONS OF TIME SERIES ANALYSIS 7

7. STEPS IN CONDUCTING TIME SERIES ANALYSIS 8

8. CONCLUSION 9

9 REFERENCES 9

ABSTRACT:

1|Page
Department of Mathematics
Time series data typically show patterns including trends, seasonal fluctuations,
irregular cycles, and sporadic changes in level or variability in the domains of
business, economics, environment, medical, and other sciences. The goals of
studying such series are frequently to detect unanticipated interventions, evaluate
the impact of known exogenous interventions, and extrapolate the dynamic pattern
in the data to forecast future observations.

INTRODUCTION:

Time series analysis is a statistical technique that deals with trend analysis and
time series data. Time series analysis made its way into medicine when the first
practical electrocardiograms (ECGs), which can diagnose cardiac conditions by
recording the electrical signals passing through the heart, were invented in 1901.
John Graunt’s actuarial tables were one of the first results of time-series-style
thinking applied to medical questions. In his book, Grant presented the first life
tables, which you may know as actuarial tables. These tables show the probability
that a person of a given age will die before their next birthday Data from time
series are periodic time periods that have been measured at regular intervals or
gathered at certain times. To put it another way, a time series is just a collection of
data points arranged chronologically, and time series analysis is the act of
interpreting this data. The Gross Domestic Product (GDP), the Consumer Price
Index, the SP 500 Index, and unemployment rates are examples of time series 1
data in economics. Time series data in the social sciences could include
information on population growth, migration patterns, birth rates, and political
variables. Here in the article, we discuss the Definitions, Assumptions, Objectives,
Application, Time series models, and Stationarity along with their way to identify

KEY CONCEPTS IN TIME SERIES ANALYSIS

Trend:
2|Page
Department of Mathematics
A trend represents the long-term direction in the data. For example, the upward
trend in the stock market over several years indicates overall growth.

Seasonality:
Seasonality refers to regular, repeating patterns within a dataset, such as higher
sales during holidays or increased electricity usage during winter months.

Cyclic Patterns:
Cyclic patterns are long-term fluctuations that are not as regular as seasonal
patterns. They are often associated with economic cycles, such as periods of
expansion and recession.

Irregular/Noise:
Irregular components or noise are random variations that do not follow a
predictable pattern. These can be caused by unexpected events or anomalies in the
data.

Stationarity:
A time series is stationary if its statistical properties (mean, variance,
autocorrelation) remain constant over time. Stationarity is a key assumption for
many time series models.

Autocorrelation:
Autocorrelation measures the correlation between current and past values in a time
series. High autocorrelation suggests that past values have a strong influence on
current values.

TIME SERIES PLOTS

3|Page
Department of Mathematics
 A time series plot is a graph that shows information gathered over time from any
process. The chart can be used to determine the historical trends in the data as well
as whether the data points are random or show any patterns.

For instance, you could want to check to see if the volume of calls coming into a
call center is constant from month to month or if there is any particular pattern in
the data, such as a diminishing trend or an increasing trend. A times series plot can
also be used to visually detect signs of stability in a process in order to ascertain its
stability.

TIME SERIES MODELS

4|Page
Department of Mathematics
Additive Model
In the additive model, we represent a particular observation in a time series as the
sum of these four components.
O=M+S+C+E
where O represents the original data, M represents the trend. S represents the
seasonal variations, C represents the cyclical variations and E represents the
irregular variations. In another way, we can write Z(t) = M(t) + S(t) + C(t) + E(t)

Multiplicative Model
In this model, four components have a multiplicative relationship. So, we
represent a particular observation in a time series as the product of these four
components:
O = MSCE

5|Page
Department of Mathematics
where O, M, S, C, and E represent the terms as in the additive model. In another
way, we can write
Z(t) = M(t)S(t)C(t)E(t) 7 .
This model is the most used model in the decomposition of time series. To remove
any doubt between the two models, it should be made clear that in the
Multiplicative model S, C, and E are indices expressed as decimal percentages
whereas, in the Additive model S, C, and E are quantitative deviations of a trend
that can be expressed as seasonal, cyclical, and irregular in nature.

6|Page
Department of Mathematics
APPLICATIONS OF TIME SERIES ANALYSIS
Finance:
Stock Price Forecasting: Predict future stock prices based on historical data.
Economic Indicators: Forecast metrics like GDP, inflation, and unemployment
rates.
Financial Risk Management: Assess and predict financial risks using time series
models.
Weather Forecasting:
Temperature Prediction: Estimate future temperatures using historical data.
Rainfall Forecasting: Predict rainfall patterns for agriculture and disaster
management.
Sales and Demand Forecasting:
Retail Sales Prediction: Estimate future sales to manage inventory and supply
chains.
Inventory Management: Optimize stock levels based on demand forecasts.

Healthcare:
Disease Outbreak Monitoring: Track and predict the spread of diseases using
historical data.
Patient Volume Forecasting: Estimate future patient admissions for resource
planning.
Energy:
Load Forecasting: Predict future energy consumption for grid management.
Renewable Energy Production Estimation: Estimate the production of solar and
wind energy.

7|Page
Department of Mathematics
STEPS IN CONDUCTING TIME SERIES ANALYSIS
Data Collection:
Gather historical data points in chronological order. Ensure data quality and
completeness.
Exploratory Data Analysis (EDA):
Visualize the data to identify trends, seasonality, and irregularities. Use tools like
line plots and histograms.
Stationarity Testing:
Use tests like the Augmented Dickey-Fuller (ADF) test to check for stationarity.
Transform data if necessary (e.g., differencing).
Model Selection:
Choose an appropriate model based on data characteristics (e.g., AR, MA,
ARIMA). Consider using model selection criteria like AIC or BIC.
Model Fitting:
Estimate model parameters using techniques like Maximum Likelihood Estimation
(MLE).
Model Diagnostics:
Check residuals to ensure they are random and normally distributed. Use
diagnostic plots and statistical tests.
Forecasting:
Generate future data points using the fitted model. Visualize the forecasts and
confidence intervals.
Model Validation:
Compare forecasts with actual outcomes to assess model performance. Use metrics
like Mean Absolute Error (MAE) and Root Mean Square Error (RMSE).

8|Page
Department of Mathematics
CONCLUSION:

Time series analysis helps in understanding and predicting temporal data by

identifying trends, seasonality, and irregular patterns. It is widely used across
various fields for forecasting and decision-making.

Importance in Various Fields:From finance to healthcare, time series analysis

provides valuable insights that drive strategic planning and operational efficiency.

Future Directions and Advancements:Ongoing research and technological

advancements continue to improve time series models and their applications,
making them more robust and accurate.

REFERENCES:

Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and

Practice. OTexts.
Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (2008). Time Series Analysis:
Forecasting and Control. Wiley.
Shumway, R. H., & Stoffer, D. S. (2017). Time Series Analysis and Its
Applications: With R Examples. Springer.

9|Page
Department of Mathematics