Predicting Gold Price Fluctuation in Indian Market

PREDICTING GOLD PRICE
FLUCTUATION IN INDIAN MARKET
Ashok Kumar
X16138422
National college of Ireland
Higher Diploma in Data Analysis

Abstract
The main idea of this exercise is to predict
the fluctuations in gold prices in India.
Where I am going to work on developing
exclusive models that are going to
describes the roles and ways of
approaching the sources that I am going to
considering. In this project I am going to
gather the data from 2008 to 2018. Which
includes the data of Indian economy, this
report explains the entire supply chain for
India’s gold market from imports and
recycling through to customer demands at
the same time gives an overview of current
policies on gold transactions and how they
have been considered over the years.
Alistair Hewitt, Director, and Market
Intelligence, World council Said: In 2016
India was one of the world’s fastest
growing economies, while the economy
was rocked by the demonetisation. By
2020 they expect Indian gold demand to
average 850t to 950t per annum. In India
Gold has higher value and is used to
protect oneself from inflation, that’s why
investors choose to acquire gold instead of
currency. When inflation is high the
demand for gold also increases and vice
versa, in that case, price of gold will
increase and cause huge demand from
customers. Any changes in the global
movement effects the price of metal in
India.
Keywords- Prediction; Fluctuation; Gold
price; Regression; India;
1 Introduction
The historical data proves that, gold
was utilized as a form of currency in
various countries, and the United States of
America is not an exception. Even today,
gold has managed to retain its value. Gold
is used as a means to assess the country’s
financial strength. India is among those
countries which buys gold and the USA,
South Africa, and Australia are those
countries which sells gold. When
compared to alternate investment options,
gold investment is considered as the safe
investment, by the small investors. As, this
commodity has the capacity to bear the in-
built investment risks. The financial
conditions of a country helps the
government to make governmental
investments in gold, and interest rates.
Because, the financial condition indicates
the country’s economic strength. If the
Global investors predict drastic decline in
the gold rates, then they find other place to
invest. In general, the gold spot rates are
decided two times per day depending on
the supply and demand in the gold market.
Any form of fractional change in the gold
price could turn out as a huge profit or loss
for the investors and the government
banks. Therefore, a daily forecast on rise
and decline of the gold rates, is beneficial
for the investors in deciding when to
purchase or sell the commodity.
1.1 Purpose
The purpose of this document is to
set out the requirements for predicting the
factors which mainly impacts the gold
price fluctuation, in the Indian market.
1.2 Project Scope
The scope of the project is to utilize
the data mining techniques to help in the
prediction of fluctuating gold price.
1.3 Project objectives
The objectives of this project is to
stress on the Data mining techniques like,
classification, clustering, regression
methods, decision tree, to predict the
fluctuation in gold price in Indian market,
for a certain period. Followed by, reading
negative consequences, and to find and
1

prove which other factors could affect the
fluctuation of price. The evidence base
will be presented, by undertaking a regular
search of current reviews.
1.4 Project expectations
This project expects to predict the
gold prices, accurately.
1.5 Project Risks
The risks for the project include
inflation, monetary policy, economic data,
supply and-demand and currency
movements, as these factors fluctuates the
gold price.
2 Literature Review
According to [1], the authors have
proved the importance of gold and its
fluctuating price prediction. Gold is valued
and is utilized as a means to assess the
country’s financial strength. The daily
forecast on rise and decline of the gold
rates, is said to benefit the investors. So, a
prediction models are developed in this
research. This research predicts the future
gold rates depending on 22 market
variables, with the help of machine
learning algorithms. The represented
results denote that the daily gold rates are
predicted accurately. The developed
prediction models are said to beneficial the
investors and the central banks, for
deciding on time to invest in gold. It is
observed that predicting the gold rate is
not an easy task. This study is
comprehensive to date, so the various
countries and companies’ economic indicators
are considered. To the contrary we show
that stock value of a major company has
more influence on the gold rates than US
economy. In future, we intend to improve
our results by using ensemble learning,
and deep learning.
As per [2], Develop a forecasting
model for predicting and forecasting gold
prices based on economic factors such as
inflation, currency price movements and
others. For investing the money, investors
are putting their money into gold because
gold plays an important role as a
stabilizing influence for investment
portfolios. Due to the increase in demand
for gold in India, it is necessary to develop
a model that reflects the structure and
pattern of gold market and forecast
movement of gold price. The most
appropriate approach to the understanding
of gold prices Support vector Regression
and decision tree model. The experimental
result will show the better performance
from these two (Decision tree algorithm
and support vector regression algorithm)
algorithms.
It is stated in [3] that, the global gold
market has recently attracted a lot of
attention and the price of gold is relatively
higher than its historical trend. For mining
companies to mitigate risk and uncertainty
in gold price fluctuations, make hedging,
future investment and evaluation
decisions, depend on forecasting future
price trends. The first section of this paper
reviews the world gold market and the
historical trend of gold prices from January
1968 to December 2008. This is followed
by an investigation into the relationship
between gold price and other key
influencing variables, such as oil price and
global inflation over the last 40 years. The
second section applies a modified
econometric version of the long-term trend
reverting jump and dip diffusion model for
forecasting natural-resource commodity
prices. This method addresses the
deficiencies of previous models, such as
jumps and dips as parameters and unit root
test for long-term trends. The model
proposes that historical data of mineral
commodities have three terms to
2