You are on page 1of 8

FORECASTING FUTURE PRICES OF

GOLD WITH TIME SERIES


A P P L I C AT I O N

FATIMA SOHAIL (19813) ZAHRA FATIMA (19798)


CRISP-DM
MODEL
 We would follow the traditional
CRISP-DM model framework to
carry out the following data mining
task on our dataset.
BUSINESS
U N D E R S TA N D I N G

 Gold, like other metals, is traded on


international commodity exchanges. We will
work with historical gold prices since 1970s to
help explain time series in a real-world scenario
and forecast its potential value.
D ATA
U N D E R S TA N D I N G

 We obtained the dataset from ‘Kaggle’ about gold


pricing information since 1970s consisting of two
columns, one for date and the other for value. For
this dataset, gold pricing is utilized from
‘Quandl’. Quandl is the premier source for
financial, economic, and alternative datasets,
serving investment professionals. About 400,000
users use Quandl's website, including analysts
from the world's leading hedge funds, wealth
managers, and investment banks. The data seems
to be very compact and clean based on the data
summary.
D ATA
MODELLING
 hj
CRISP-DM
MODEL

 hj
CRISP-DM
MODEL

 hj
CRISP-DM
MODEL

 hj

You might also like