Project Report on

Forecasting of Crude Prices

Submitted to Prepared by
Ms. Smruti Bulsari Kashyap Bhatt(07-A)
(Prof.,DBIM,VNSGU,Surat) Hiten Bharti(06-A)
Rinkesh Chaudhari(11-A)
Keyur Chauhan(14-A)

Department of Business & Industrial Management

Veer Narmad South Gujarat University, Surat

Preface
As today’s whole world is depend on crude at some what level, and the
prices of crude oil is very fluctuating in the last decade due to many turning
phase of economy of the globe. For this we can say that in the month of July
– 08 crude prices were at 142$/bl and in just six months they came steeply
to 33$/bl. So, one can imagine that how it affects the whole economy. We
can see same fluctuation in india in petrol/diesel prices as they are directly
related to crude.

Main objective of this study is to forecast crude prices with the use of Moving
Averages.
ACKNOWLEDGMENTS
We would firstly like to thank Almighty for his blessings have made it
possible today.

We would like to thank Ms. Smruti Bulsari ( Professor, DBIM, VNSGU ) for
providing Guidance & Support for this Report.

Next We would like to thank DBIM and authorities for providing environment
for the successful completion of the report. (Labs & Library Resources)

We would like to thank all the people associated directly or indirectly with
this report.
Index
What is Crude???

Why Crude???

History

OPEC

Forecasting

Methods for forecasting

Moving Average

RMSE Values

Summary
What is Crude???
A mixture of hydrocarbons that exist in a liquid phase in natural
underground reservoirs and remains liquid at atmospheric pressure after
passing through surface separating facilities.

Why Crude???
As the prices of the crude are very volatile it made a high of 142$/bl in the
month of july – 2008 and came down to 33$/bl in just six months. So, one
understand that how much it is volatile. Volatility is the main thing in this
type of commodity because Crude is Considered as “Black Gold”. In
automobiles, jet planes, production, cooking everywhere indirectly crude is
used. Even we can say that without crude it is impossible to do anything.
That’s why it is sound to be interesting to forecast the crude prices.

In India there are many refineries like Reliance, Essar, Bharat Petroleum,
IOC, HPCL, MRPL etc. they all are dependent on crude that produced outside
India.

It is prideful to say that every one barrel out of four barrel of crude that
OPEC (Organization of Petroleum Exporting Countries ) produces is coming
at RIL, Jamnagar for refinement. So, it is a capacity of only one company
Reliance so we can say that there are very large amount of capacity here for
refinement. As numbers says now we can also think about that as large no.
of refineries are there; all their profit/loss is directly vary with crude prices.
Either it is a govt. sector or private sector. So, in terms of foreign
fund/revenue there is a large volatility which varies directly with variation in
crude prices.

History
Below graph shows the crude prices from 1973 to 2009 ( appx. Of 36
years). It is a graph of Crude prices ( $ ) Vs. Production of Crude ( thousand
barrels per day ).
While talking about crude or crude prices generally we came across one
name that is OPEC. Now let’s see What is OPEC???

OPEC is a permanent, intergovernmental organization, established in

Baghdad, Iraq, 10–14 September 1960. The Organization now comprises 13
Members:

Algeria, Angola, Ecuador, Indonesia, Islamic Republic of Iran, Iraq,

Kuwait, Socialist People’s Libyan Arab Jamahiriya, Nigeria, Qatar, Saudi
Arabia, United Arab Emirates and Venezuela.

The Organization has its headquarters in Vienna, Austria. Its objective

is to coordinate and unify petroleum policies among Member Countries, in
order to secure a steady income to the producing countries; an efficient,
economic and regular supply of petroleum to consuming nations; and a fair
return on capital to those investing in the petroleum industry.
Forecasting
Most Business decisions are made in the face of risk or uncertainty. A firm
must decide how much of each product to produce, what price to change,
and how much to spend on advertising, and it must also plan for the growth
of the firm. All these decisions are based on some forecast of the level of
future economic activity in general and demand for the firm’s product(s) in
particular. The aim of economic forecasting is to reduce the risk or
uncertainty that the firm faces in its short – term operational decision
making and in planning for its long term growth.

Forecasting techniques range from very naïve ones that require little effort
to very sophisticated ones that are very costly in terms of time and effort.
Some forecasting techniques are basically qualitative, while others are
quantitative. Some are based on examining only past values of the data
series to forecast its future values; others involves the use of complex
models based on a great deal of additional data and relationships. Some are
performed by firm itself; others are purchased from consulting firms.

Forecasting depends on…

The cost of preparing the forecast and the benefit that results from its use

The lead time in decision making

The time period of the forecast ( short term or long term )

The level of accuracy required

The quality and availability of the data

The level of complexity of the relationships to be forecasted.

In general, the greater the level of accuracy required and the more complex
the relationships to be forecasted, the more sophisticated and expensive will
be the forecasting exercise.
Methods for Forecasting
Qualitative Forecasts

Time Series Analysis

Smoothing Techniques

Barometric Methods

Econometric Models

Qualitative Forecasts

Surveys and opinion polls are often used to make short – term forecasts
when quantitative data are not available. These qualitative techniques can
also be useful for supplementing quantitative forecasts that anticipate
changes in consumer tastes or business expectations about future economic
conditions. They can also be invaluable in forecasting the demand for a
product that the firm intends to introduce.

Time Series Analysis

One of the most frequently used forecasting methods is time – series

analysis or the analysis of time – series data. Time – series data refers to
the value of a variable arranged chronologically by days, weeks, months,
quarters, or years.

The first step in time – series analysis is usually to plot past values of the
variable that we seek to forecast on the vertical axis and time on the
horizontal axis in order to visually inspect the movement of the time series
over time. Time – series analysis attempts to forecast future values of the
time series by examining past observation of the data only. The assumption
is that the time series will continue to move as in the past.
Smoothing Techniques

Other methods of naïve forecasting are smoothing techniques. These predict

values of a time series on the basis of some average of its past values only.
Smoothing techniques are useful when the time series exhibit little trend or
seasonal variations but a great deal of irregular or random variation. The
irregular or random variation in the time series is then smoothed, and future
values are forecasted based on some average of past observations.

Barometric Methods

One way to forecast or anticipate short – term changes in economic activity

or turning points in business cycles is to use the index of leading economic
indicators. These are time series that tend to precede ( lead ) changes in the
level of general economic activity, much as changes in the mercury in a
barometer precede changes in weather conditions ( hence the name
“barometric methods”).

Econometric Models

The firm’s demand and sales of a commodity as well as many other

economic variables are increasingly being forecasted with econometric
models. The characteristic that distinguishes econometric models from other
forecasting methods is that they seek to identify and measure the relative
importance of the various determinants of demand or other economic
variable to be forecasted. Econometric forecasting frequently incorporates or
uses the best features of other forecasting techniques, such as trend and
seasonal variations, smoothing techniques and leading indicators.

Which forecasting method a firm chooses depends on six points:

1. The cost of preparing the forecast and the benefit that results from its
use

2. The lead time in decision making

 3. The time period of the forecast

4. The level of accuracy required

5. The quality and availability of data

6. The level of complexity of the relationships to be forecast.

Moving Averages
The simplest smoothing technique is the moving average. Here the
forecasted value of a time series in a given period ( month, quarter, year,
etc. ) is equal to the average value of the time series in a number of
previous periods. For example, with a three – period moving average, the
forecasted value of the time series for the next period is given by the
average value of the time series in the previous three periods. Similarly,
with a five – period moving average, the forecast for the next period is equal
to the average for the previous five periods and so on. The greater the
number of periods used in the moving average, the greater is the smoothing
effect because each new observation receives less weight. This is more
useful the more erratic or random is the time – series data.

USES FOR MOVING AVERAGES

There are many uses for moving averages, but three basic uses stand out:

 Trend identification/confirmation
 Support and Resistance level identification/confirmation
 Trading Systems

TREND IDENTIFICATION/CONFIRMATION

The trend identification technique uses the direction of the moving average
to determine the trend. If the moving average is rising, the trend is
considered up. If the moving average is declining, the trend is considered
down. The direction of a moving average can be determined simply by
looking at a plot of the moving average or by applying an indicator to the
moving average.
SUPPORT AND RESISTANCE LEVEL IDENTIFICATION/CONFIRMATION

Another use of moving averages is to identify support and resistance levels.

This is usually accomplished with one moving average and is based on
historical precedent. As with trend identification, support and resistance level
identification through moving averages works best in trending markets.

TRADING SYSTEMS

A trading system is simply a group of specific rules, or parameters, that

determine entry and exit points for a given equity. Let’s see how moving
average is useful in trading systems. For example, two moving average
parameters, the long-term and the short-term, to create a rule "buy when
the short-term crosses above the long term, and sell when the opposite is
true."

Month Actual MA(2) A–F (A-F)^2

Price($)
Jan-06 58.48
Feb-06 56.62
Mar-06 57.87 57.55 0.32 0.1024
Apr-06 64.44 57.245 7.195 51.768025
May-06 65.11 61.155 3.955 15.642025
Jun-06 64.6 64.775 -0.175 0.030625
Jul-06 68.89 64.855 4.035 16.281225
Aug-06 68.81 66.745 2.065 4.264225
Sep-06 59.34 68.85 -9.51 90.4401
Oct-06 54.97 64.075 -9.105 82.901025
Nov-06 55.42 57.155 -1.735 3.010225
Dec-06 57.95 55.195 2.755 7.590025
Jan-07 51.09 56.685 -5.595 31.304025
Feb-07 52.9 54.52 -1.62 2.6244
Mar-07 57.82 51.995 5.825 33.930625
Apr-07 64.05 55.36 8.69 75.5161
May-07 65.05 60.935 4.115 16.933225
Jun-07 66.08 64.55 1.53 2.3409
Jul-07 73.35 65.565 7.785 60.606225
Aug-07 74.98 69.715 5.265 27.720225
 Sep-07 74.24 74.165 0.075 0.005625
Oct-07 80.12 74.61 5.51 30.3601
Nov-07 88.29 77.18 11.11 123.4321
Dec-07 89.16 84.205 4.955 24.552025
Jan-08 90.69 88.725 1.965 3.861225
Feb-08 91.71 89.925 1.785 3.186225
Mar-08 100.23 91.2 9.03 81.5409
Apr-08 107.87 95.97 11.9 141.61
May-08 120.26 104.05 16.21 262.7641
Jun-08 128.16 114.065 14.095 198.669025
Jul-08 137.18 124.21 12.97 168.2209
Aug-08 114.46 132.67 -18.21 331.6041
Sep-08 97.78 125.82 -28.04 786.2416
Oct-08 75.46 106.12 -30.66 940.0356
Nov-08 49.85 86.62 -36.77 1352.0329
Dec-08 37.72 62.655 -24.935 621.754225
Jan-09 38.54 43.785 -5.245 27.510025
Feb-09 42.99 38.13 4.86 23.6196
Mar-09 46.5 40.765 5.735 32.890225
Apr-09 50.48 44.745 5.735 32.890225
May-09 53.67 48.49 5.18 26.8324
Jun-09 66.58 52.075 14.505 210.395025
Jul-09 66.07 60.125 5.945 35.343025
Aug-09 72.86 66.325 6.535 42.706225
Sep-09 67.71 69.465 -1.755 3.080025
Oct-09 71.12 70.285 0.835 0.697225

In the above table the first and second columns shows the time period
( month ) and actual prices of crude in U.S.$/bl respectively. Here the data
seem to show considerable random variation but no secular or seasonal
variation. Column 3 gives the calculated moving average. For example, MA
(2) is 57.55 is obtained by adding the first two values in column 2 and
dividing by 2, that is, (58.48+56.62)/2 = 57.55. This compares with the
actual value (A) that is 57.87 for the next month. Now, dropping the first
value in our actual price list and take new value which one is of next month
and we get new Moving Average with the use of that.
We have to calculate the root-mean-square-error (RMSE) of each forecast and
use the moving average results in the smallest RMSE. The formula for root-mean-
square error (RMSE) is

RMSE = √∑ ❑( At −Ft )2
n

Here At = the actual value of the time series period t

Ft = the forecasted value

N=number of periods or observations.

The forecast difference or error (A-F) is squared in order to penalize larger errors
proportionately more than smaller errors.

Now after analyzing the RMSE of all 46 months, the smallest value of RMSE is
considered and forecasted value of that moving average forecast is considered.

RMSE Values :

Month RMSE
MA(2) 11.70
MA(3) 07.89
MA(4) 17.43
MA(5) 19.81
MA(6) 21.78
MA(7) 23.36
MA(8) 24.63
MA(9) 24.96
MA(10) 26.58
MA(11) 27.29
MA(12) 27.94

In the above table as we seen that we got RMSE values for 11 months. In
all that the minimum RMSE value is 07.89 which is of MA(3). So we can take
MA(3) for further prediction.

And, by using we have predicted the next month’s crude price is 72.07$/bl.

Summary

Moving averages can be effective tools to identify and confirm trend, identify
support and resistance levels, and develop trading systems. However,
traders and investors should learn to identify securities that are suitable for
analysis with moving averages and how this analysis should be applied.

Now, come to this particular case, here we want to add some facts that all
financial markets like our stock market, commodity all are open markets. In
just one day or even in one second any thing can happen. Moving averages
are very important and also they are widely used by financial institutions,
Brokers ( Commodity as well as Stock Brokers ), Investors etc. We are not in
oppose of theoretical aspects but it is a general talk. So, at last we
summarize this topic of forecasting with that it is very useful tool and it is
also used by people all over the world (with us also) for buying or selling
stocks/commodity.
Bibliography
Websites
http://www.google.com/

http://www.mcxindia.com/

http://www.opec.org/

http://www.wikipedia.com/

http://www.marwadionline.com/

http://www.ashikadirect.com/

Books
Managerial Economics by Dominick Salvatore