30
 Market Research on Bollywood Movies Success Prediction Modelling Submitted To Dr. Atanu Adhikari Marketing Management II Course I.I.M. Kozhikod e By Bharat Subramony PGP/16/012 Gunveer Singh PGP/16/019 Ranjan Sharma PGP/16/040 Rohit Singla PGP/16/043 Utkarsh Rastogi PGP/16/056

A3 Bollywood Movies

Embed Size (px)

Citation preview

Page 1: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 1/30

 

Market Research on

Bollywood MoviesSuccess Prediction Modelling

SubmittedTo

Dr. Atanu AdhikariMarketing Management II Course

I.I.M. Kozhikode 

By

Bharat Subramony PGP/16/012

Gunveer Singh PGP/16/019

Ranjan Sharma PGP/16/040

Rohit Singla PGP/16/043

Utkarsh Rastogi PGP/16/056

Page 2: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 2/30

Table of Contents

ACKNOWLEDGEMENT ....................................................................................................... 3 

ABSTRACT .............................................................................................................................. 4 

INTRODUCTION.................................................................................................................... 5 

LITERATURE REVIEW ....................................................................................................... 6 

DATA PREPARATION AND CLEANING .......................................................................... 9 

CODING ................................................................................................................................... 9 

DATA CLEANING ..................................................................................................................... 9 

IMPORTING DATA IN SPSS ....................................................................................................... 9 

METHODOLOGY ................................................................................................................ 10 

SAMPLING ............................................................................................................................. 10 

MEASUREMENT AND SCALING .............................................................................................. 10 

QUALITATIVE METHOD ......................................................................................................... 10 

QUANTITATIVE METHOD....................................................................................................... 11 

ANALYSIS & RESULT ........................................................................................................ 12 

SINGLE VARIABLE R EGRESSION ............................................................................................ 12 

CONJOINT A NALYSIS............................................................................................................. 17 

CLUSTER A NALYSIS .............................................................................................................. 21 

DISCUSSION ......................................................................................................................... 25 

LIMITATIONS OF THE STUDY ....................................................................................... 27 

FUTURE RESEARCH .......................................................................................................... 27 

WORKS CITED..................................................................................................................... 28 

QUESTIONNAIRE.................................................................................................................... 29 

CARD FOR DUMMY VARIABLE ANALYSIS ............................................................................... 30 

Page 3: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 3/30

Acknowledgement

A journey is easier when you travel together. Interdependence is certainly more valuable than

independence. This report on  Market Research on Bollywood Movies and Modelling a

Success Prediction System is the result of work whereby we have been accompanied and

supported by many people. It is a pleasant aspect that we have now the opportunity to express

our gratitude for all of them for their valuable guidance, for devoting their precious time,

sharing their knowledge and their co-operation throughout the course of development of our 

 project idea and the academic years of education.

With immense pleasure we express our sincere gratitude, regards and thanks to our projectguides Prof. Atanu Adhikari for their excellent guidance, invaluable suggestions and

continuous encouragement at all the stages of our project work. We would like to thank the

staff of Crown Theatre for cooperating and assisting us in conducting our market research.

We would also like to thank the participants of Focus Group Discussions and interviews. And

finally we thank God Almighty for all that he has endowed us with and his blessings.

Group No. A3

Bharat Subramony PGP/16/012

Gunveer Singh PGP/16/019

Ranjan Sharma PGP/16/040

Rohit Singla PGP/16/043

Utkarsh Rastogi PGP/16/056

Page 4: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 4/30

Abstract

The project aims at formulating a mathematical model to predict the success of a mainstream

 bollywood movie, based on parameters which influence it. The are obtained by secondary

data sources and insights from primary resources. Exploratory research has been conducted to

arrive at the most influential parameters. In this project, we have used Descriptive and

Statistics Analytical tools to assist in arriving the model proposition. The result of this project

is a reasonably accurate estimator of the success of any bollywood movie, even before its

inception, under given conditions of influential attributes, and help shape the future of 

 bollywood industry.

Keywords : Mathematical model, attributes, exploratory, success.

Page 5: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 5/30

Introduction

Bollywood is the informal term popularly used for the Hindi-language film industry based

in Mumbai, Maharashtra, India. Bollywood churns out around 800 movies every year.

While some movies end up into blockbusters, some fail miserably at the box office. The

increased emergence of educated middle class renders Bollywood movies into open

competition not only with other Bollywood movies but Hollywood too. It is one of the

largest employment generating industries of the Indian economy. Today, the growth of this

industry is quite phenomenal with the changing preferences of movie-goers and filmmakers. Some of the Bollywood movies involve funds running into millions of dollars. There is a lot

of fortune at stake in the performance of movies at the box office.

With this in mind, this project steers to first understand the viewer‟s perspectives about the

 bollywood industry. There are several factors that lead to a person liking or disliking a

movie. It could range from the traumatic experience in ticket queue, to a bad or noisy

neighbour in the cinema hall, or even mal-functioning air-conditioning system. So how do

we arrive at conclusive factors? The fact remains that there are much more factors affecting

the success of a movie, than just these nimble parameters. There have been cases of movies

like Sholay, which were initially declared a flop, simply because it was ahead of its time,and then in a matter of 6 months, it was a blockbuster. Or take the case of a superlow

 budget movie called Stanley Ka Dabba, which bombed in box office, and won several

critical acclaims. Bollywood is nothing if not unpredictable

In this project, we first use exploratory research techniques such as Focus Group

Discussion, Group Interviews, and survey questionnaires, to absorb the opinion of the

viewers. Based on the respondent‟s perspective about the movie, we shall try to map the

attributes to the success or failure, as perceived by the producer and the viewer. This project

has the potential to advise leading production houses and film-makers about what are the

 basic dos and donts to guarantee success and avoid rapid stagnation of revenues from post-

release shows.

Page 6: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 6/30

Literature Review

Almost all existing studies use total domestic box office sales as a dependent variable

(Basuroy et al., 2003; Chang and Ki, 2005; Hennig-Thurau et al., 2007; Litman, 1982;

Litman, 1983; Ravid, 1999; Wyatt, 1999). Few studies use domestic and worldwide box

office sales together (Litman and Ahn, 1998). Using worldwide box office sales causes some

inconsistencies because it includes uncontrolled country-level variables such as political,

legal and cultural factors that could affect box office performance (Oh, 2001). Some studies

have used a film‟s opening week sales as a dependent variable (Elberse and Eliashberg, 2003)

and other have used opening week sales also as an independent variable since they believe

that the early box office performance of a film (i.e. opening week) has a strong influence on a

film‟s overall sales (DeVany and Walls, 2002; Walls, 2005). According to this assumpt ion,

audiences are more inclined to see a film once they know that many other people have seen it.

This has been confirmed by several empirical studies such as those by Elberse and Eliashberg

(2003) or Hennig-Thurau et al. (2007). For our study, we selected opening week sales as well

as total box office sales as dependent variables in order to compare the results.

The majority of studies in the literature use common variables such as genre (Chang and Ki,

2005; DeVany and Walls, 2002; Litman, 1982; Litman, 1983; Litman and Kohl, 1989;

Simonoff and Sparrow, 2000; Wallace et al.,1993; Walls, 2005; Zuckerman and Kim, 2003),

MPAA rating (Basuroy et al.,2003; Chang and Ki, 2005; Hennig-Thurau et al.,2007; Litman,

1982; Litman, 1983; Litman and Kohl, 1989; Ravid, 1999; Sochay, 1994; Sawhney and

Eliashberg, 1996; Sharda and Dursun, 2002; Walls, 2005), star or director power (Basuroy et 

al., 2003; Chang and Ki, 2005; Elberse, 2007; Elberse and Eliashberg, 2003; Hennig-Thurau

et al.,2007; Litman, 1982; Litman and Kohl, 1989; Ravid, 1999; Soichay, 1994; Walls, 2005;

Zuckerman and Kim, 2003), season of release (Basuroy et al.,2003; Chang and Ki, 2005;

Elberse and Eliashberg, 2003; Litman, 1982; Litman, 1983; Litman and Kohl, 1989; Sharda

and Dursun, 2002; Simonoff and Sparrow, 2000; Walls, 2005; Zuckerman and Kim, 2003),

and number of screens (Basuroy et al.,2003; Chang and Ki, 2005; Chen, 2002; Elberse and

Eliashberg, 2003; Hennig-Thurau et al.,2006; Litman and Kohl, 1989; Sharda and Dursun,

2002; Sochay, 1994; Zuckerman and Kim, 2003). Some studies also use distribution power as

a predictor of box office sales (Chang and Ki, 2005; Chen, 2002; Shugan and Swait, 2000). A

few studies have used audience review (Basuroy et al.,2003; Chang and Ki, 2005; Elberse

Page 7: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 7/30

and Eliashberg, 2003; Liu, 2006; Hennig-Thurau et al.,2007; Dellarocas et al., 2007; Duan,

Gu and Whinston, 2008).

Previous studies have used four variables but the required information either was not at all or 

mostly not available for the Indian films selected for our study. Therefore, we could not use

those variables. The first variable is sequel films (e.g. Lehman and Weinberg, 2000), also it

should be noted that some researchers did not find significant effects at the box office

(Basuroy et al., 2003). For another variable, budget, Hennig-Thurau et al. (2006) and Elberse

and Eliashberg (2003) found that production budgets play a relatively small role in movies‟  

financial success. For the third variable - film criticism in the media - studies show

contradictory results. Sawhney and Eliashberg (1996) and Eliashberg and Shugan (1997)

found a positive relationship while Ravid (1999) and Reinstein and Snyder (2005) maintain

that film critics are not effective predictors of box office sales. For the fourth variable -

number of prior awards received by participants in the current film (Dodds and Holbrook,

1988) - studies by Basuroy et al. (2003) and Simonoff and Sparrow (2000) showed that this

variable has no relevance to a film‟s total performance. Besides, awards are usually decided

after a movie is released and thus have no effect on early sales (Chang and Ki, 2005).

As a concept, the experience goods property model is closely related to a movie audience‟s

decision-making. Movies are experienced goods as the consumption experience is an end in

itself (Reddy et al., 1998) and consumers do not know the value of a movie until they

experience it (Shapiro and Varian, 1999). Unlike the study of Reddy et al. (1998), our study

uses variables related to brand and distribution. And unlike Chang and Ki (2005), our study

uses opening week box office sales also as an independent variable to predict total box office

sales. Moreover, previous researchers mostly adopted independent variables without

categorizing them. Such categorization can help to generate new variables based on

guidelines from the process (Chang and Ki, 2005). Few researchers have categorized

independent variables based on marketing characteristics of movies. Litman and Ahn (1998)

grouped their independent variables into production stage, distribution stage, and exhibition

stage. Reddy et al. (1998) grouped them into information sources and objective features

while Hennig-Thurau et al. (2006) grouped the independent variables into two categories,

studio actions and movie quality. Chang and Ki (2005) divided variables into brand-related,

objective features, information source and distribution-related variables.

Page 8: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 8/30

Based on the discussion above, we categorize the independent variables into four mutually

exclusive categories: variables related to product, brand, distribution and consumers. Product-

related variables pertain to the category and genre of a film and cannot be influenced by the

audience. Brand-related variables refer to the reputation of the actors or stars and the director 

and are strongly related to the “product.” Distribution-related variables include not only the

timing or season the film is released but the number of screens and the marketing power of 

the film‟s studio or distribution companies. Consumer -related variables play a role once the

film is released and reflect consumer behavior in terms of opening week sales and audience

reviews. The following section introduces the proposed research model illustrated in Figure 1

along with the underlying hypotheses for each category of variables.

Page 9: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 9/30

Data Preparation and Cleaning

The questionnaire was floated as mentioned above to a convenient sample. A total of 60

responses were received from respondents within Indian Institute of Management Kozhikode.

However this data could not directly be used for statistical analysis. Hence the collected data

is cleaned in the following steps –  

Coding

Each of the questions from the questionnaire was assigned a specific code. Also the responses

were given specific code for the ease of analysis in SPSS statistical tool. E.g. Questions based

on Likert scale i.e. questions asking their behavior towards a particular situation based on

nine parameters had five options to choose from viz. “Most preferable” to “Least Preferable”.“Most Preferable” option was assigned value of 1 and subsequently “Least Preferable” was

given value of 5. Then to develop the data further, the data file is downloaded in EXCEL

format. The sheet contains each response in a separate row.

Data Cleaning

Out of the 60 responses that were collected, 2 responses were not complete and the responses

were not given properly. Hence those 2 responses were deleted from the data file. Then

consistency checks were also performed on the data file. This included checking the

responses for extreme values and checking the logical consistency of the responses. Also

missing responses were substituted with neutral answer values. This cleaned data was used

for performing descriptive analysis using EXCEL software as shown later.

Importing data in SPSS

After cleaning the data, the data analysis strategy was formulated. Then the EXCEL data file

was imported into SPSS software. The data was again checked for logical consistency.

Page 10: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 10/30

Methodology

Sampling

To obtain the information about the preferences of different attributes of a movie, a sample

was conducted. The target population is the people from age group 18-30 who constitute the

major number of moviegoers. Sampling unit is the respondent him/herself because

assessment of responses was done directly. The extent for the target population was kept

confined to Kozhikode City only. Sampling frame is the student community of IIM

Kozhikode and crowd at Crown Theatre in Kozhikode. To avoid the replacement,

respondents were asked not to participate if they had taken the survey before. Sampling

techniques used to approach the respondents are Convenience and Judgmental sampling.

Putting survey on social media groups related to IIM Kozhikode, while approaching people

directly at Crown Theatre, we did judgmental sampling & convenience sampling. These

sampling techniques may not be highly accurate estimate of population characteristics but

these sampling techniques made information collection quick and easy.

Measurement and Scaling

Measurement means assigning numbers to characteristics of objects. To assign numbers to

different attributes that might affect the viewership of a movie, we use ordinal scale. An

ordinal scale helps in determining whether a movie is affected more or less by an attribute,

 but not how much more or less. The scaling technique used is non-comparative scales and for 

scaling process balanced and Likert scales were used.

Qualitative Method

The group used focus group discussion method for identifying and understanding the

qualitative aspects to be studied as well as attributes required for quantitative analysis. It

helped to identify the desired attributes of a good movie for a respondent. There were 4 male

and 3 female students at IIMK as participants between the age group of 20  – 26 years. The

questions were structured broadly into 5 categories based on literature review-

o  Favorite movies

o  Perceived attributes behind favorite movies

o  Expected attributes from a good movie

o  Decision making to go for a movie

o  Actors involved in the movie

Page 11: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 11/30

o  Awareness about the recent launches

The key findings of the focus discussion were:

o  There was a perception that established actors generally come up with good

movies

o  Music also played a significant role in deciding a movie to watch

o  There was a general consensus amidst the participants that good script is

appreciated by everyone if presented nicely

o  Word of mouth emerged as a very effective way of communication as people

listen to the opinion of friends and relatives

o  Most people wanted entertainment only so item songs were also counted

o  Controversy creates the curiosity to know about the movie

Quantitative Method

For collection of data for the exploratory study, a questionnaire survey was conducted to

understand the preferences of the respondents among the different attributes. The

questionnaire was designed incorporating the findings from a thorough literature review and

focus group discussion undertaken by the group. Before the survey was floated for collection

of responses, trial surveys were filled by 5 respondents, followed by a discussion about the

survey. The group was able to identified gaps in framing the questions, intention of the

answer options, and overall flow of the questions. Based on this feedback, changes were

made in the questionnaire. Following which, an online survey was designed to collect

responses from students of IIM Kozhikode within minimal time. To obtain information

regarding the preferences of people at Crown Theatre flash cards with questionnaire were

used. Most answer options were devised on likert scale to understand degree of variation in

responses. ( Refer to appendix)

Page 12: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 12/30

Analysis & Result

Single Variable Regression

Based on the primary and secondary data aggregated, we try to single out the most relevant

factors influencing the viewer‟s decision to watch a movie or not. As previously mentioned

these, factors include, the critic rating received, the star cast, opening week sales, the success

of pre-release music, number of item songs in the movie, the story line, whether it involves a

controversy or not, and the production house.

Hypothesis 1a: The success of the movie is independent of critic ratings it receives

Hypothesis 1b: The critic rating drives the success of a movie, in terms of gross revenue

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 5.147 1 5.147 3.540 .064b 

Residual 104.691 72 1.454

Total 109.838 73

a. Dependent Variable: RevScore

b. Predictors: (Constant), RMrate

From the above determined ANOVA table, and Coefficients table, we determine that, for 

significance level above 6.4%, the alternate hypothesis holds, true, and there exists a definite

relation between the critic rating and gross revenue of the movie.

Same test is now repeated for the ratings received in national dailies, which, we have taken

here as the Times of India, being the largest selling daily, must have the most influence on

viewers of any movie, and their decision of watching it or not.

Page 13: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 13/30

 

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 2.072 1 2.072 1.385 .243b 

Residual 107.765 72 1.497

Total 109.838 73

a. Dependent Variable: RevScore

b. Predictors: (Constant), ToIrate

It appears, that for the same significance levels as held by the critic rating, the national daily

doesn‟t quite have an influence on revenues generated for the movie. On the other hand, the

viewer‟s response on the movie is greatly influenced by the critic rating.

Hypothesis 2a: Critic rating does not influence viewer‟s opinion of a movie 

Hypothesis 2b: Critic rating influences the viewer‟s opinion about the movie. 

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 56.018 1 56.018 32.362 .000b 

Residual 124.631 72 1.731

Total 180.649 73

a. Dependent Variable: Scoreb. Predictors: (Constant), RMrate

From the above coefficients table, we can conclude that, there is a very significant effect of 

the way the critic rating influences the viewer‟s judgment about the movie, and therefore

their decision of watching a movie or not.

 Now, we try to determine the influence of the production house upon the viewer‟s opinion of 

the movie and the gross revenues earned, which is one of the important decisions for any

movie-watcher.

Page 14: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 14/30

Hypothesis 3a: The production-house does not influence decision to watch a movie

Hypothesis 3b: The production-house influences the decision to watch a movie

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression .695 1 .695 .459 .500b 

Residual 109.142 72 1.516

Total 109.838 73

a. Dependent Variable: RevScore

b. Predictors: (Constant), Productionhouse

From the above analysis, we can conclude that merely the presence of a big production house

doesn‟t influence the decision of a movie watcher to go see a movie, and has no influence on

the revenues grossed, over its time at the box office. This argument can be substantiated by

the new found awareness of movie-watchers, that big banners, try and make a fool out of 

them, by fudging up a movie, with high profile actors (as quoted by one respondent).

 Now we determine the influence of star-cast on the decision to watch a movie.

Hypothesis 4a: Star-cast doesn‟t influence the decision to watch a movie. 

Hypothesis 4b: Star-cast influences the decision to watch a movie.

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 1.640 1 1.640 1.091 .300b 

Residual 108.198 72 1.503Total 109.838 73

a. Dependent Variable: RevScore

b. Predictors: (Constant), EstdStarcast

There appears to be a fair influence of the star-cast, on the decision to watch a movie, but this

correlation is observable and significant only above 30% level of significance. This can be

attributed to the recent string of movies, which in spite of having low-key actor/actress, have

succeeded at the box-office due to several other factors, involved.

Page 15: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 15/30

 Now, we shall try and determine the influence of the release period of a movie. It has been

noticed that a number of movies were released adjusting to the proximity of festivities in

India, because, the viewers have ample time to spend with family and friends, and therefore

watch the movie.

Hypothesis 5a: Release of a movie during festivals doesn‟t influence the success of a movie.  

Hypothesis 5b: Release of a movie during festivals influences the success of a movie.

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 2.303 1 2.303 1.542 .218b 

Residual 107.535 72 1.494

Total 109.838 73

a. Dependent Variable: RevScore

b. Predictors: (Constant), Festive

From the linear regression performed for the sample, it has been observed that there is an

appreciable influence of the proximity of festivals or release of a movie during festivals,

which successfully translates into increased revenues for movie. This correlation is of high

significance above 25% level of significance, and the null hypothesis rejected.

Hypothesis 6a: Use of special promotions doesn‟t influence the initial opinion of movie.

Hypothesis 6b: Use of special promotions influences the post-release opinion of a movie.

ANOVAa

 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 11.888 1 11.888 5.946 .017b 

Residual 143.963 72 1.999

Total 155.851 73

a. Dependent Variable: QuickRate

b. Predictors: (Constant), Promotions

Page 16: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 16/30

It is an easy conclusion that the early opinion about a movie determines the initial success of 

a movie. And this opinion is substantially supported by the results of a linear regression

 performed on these variables. The null hypothesis rejected.

Hypothesis 7a: The gross earnings of a movie are independent of the first week sales.

Hypothesis 7b: The first week earnings influence the gross earnings of a movie.

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 204280.881 1 204280.881 162.464 .000b 

Residual 90532.074 72 1257.390

Total 294812.955 73

a. Dependent Variable: Gross

b. Predictors: (Constant), FWactual

The linear regression results in a very high rejection of the null hypothesis, as the first week 

sales largely determine the future course of the movie, sometimes through word-of-mouth

operations, during its tenure at the box office. However, since the two variables are being

studied neglecting the linearity or the impact of other variables, we need to accommodate for 

some room for error, which may arise from the formation of factors of independent variables.

We shall look at one last variable that can have a significant impact on the initial success and

the eventual gross earnings of the movie, which is the number of screens used for release.

Hypothesis 8a: The gross earnings of a movie are independent of number of screens used

Hypothesis 8b: The number of screens influences the gross earnings of the movie.

ANOVAa 

Model Sum of Squares

df Mean Square F Sig.

1

Regression 60243.806 1 60243.806 26.278 .000b 

Residual 114627.487 50 2292.550

Total 174871.293 51

a. Dependent Variable: Gross b. Predictors: (Constant), Screens

Page 17: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 17/30

ANOVAa 

Model Sum of 

Squares

df Mean Square F Sig.

1

Regression 11203.302 1 11203.302 46.243 .000b 

Residual 12113.525 50 242.271

Total 23316.827 51

a. Dependent Variable: FWactual

b. Predictors: (Constant), Screens

From the above results of linear regression, we can conclude that the null hypothesis stands

rejected, and that higher the number of screens used for release, greater the impact on the

initial revenue and eventually on the gross earnings.

Conjoint Analysis

From the single regression, we have been able to highlight some independent variables,

which have a significant impact on the overall success of the movie, but we now need to

understand the part worth of each attribute, of the film, i.e. variables such as budget, critic

rating, star-cast, first-week sales, originality of story, controversies in movie making, success

of the music release, special promotion techniques used for better advertising. These are dealt

together in conjoint analysis.

The attributes used in conjoint analysis are as follows,

  Ultra low budget (< 3 crores rupees), low budget ( < 10 crore rupees), medium budget (<

40 crore rupees), high budget (> 40 crore rupees)

  Low First Week sales (< 0.8x Budget), Medium First Week sales (< 1.5x Budget) and

High First week sales (> 1.5x Budget)

  Low Rajiv Masand Rating (2 or less), Medium Rajiv Masand Rating (~3) and High Rajiv

Masand rating (4 and above)

  Low Times of India Rating (2.5 or below), Medium ToI rating (3.5 or below) and High

ToI rating (3.5 and above)

Page 18: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 18/30

  Presence of famous stars in movie, inclusion of item songs, success of pre-release music,

release during festive season, U/A rating, originality of story, controversies, magnanimity

of production house/director, use of special promotion strategies

Based on the above attributes, we defined the dummy variable for analysis as a movie, with

ultra low budget, low first week sales, low Rajiv Masand Rating, low Times of India rating,

absence of famous stars, no item numbers, small production house, original story and not

released during festive season. We produced sample cards consisting of five movies each,

and asked the respondents to rate these movies out of 10, on an integer scale, then aggregated

the data for 74 bollywood movies, and proceeded for conjoint analysis, the results of which

shall be now shown.

The gross revenue, the viewer opinion and the initial review, here quoted as the QuickRate,

have been scaled to integer upto 10, such that, each integer is associated with a range for 

multiplier factors, which would give the user the expected revenue in the first week after 

release or the gross revenue as the case maybe.

Let‟s first take the prediction modelling of the first week sales of a movie, before its release

or even it conception, using a proxy called QuickRate. The regression equation would be,

 

Where, is the initial score obtained for the dummy variable.

Upon conjoint analysis, using the data points for the 74 movies, and the ratings evaluated

from respondents, we obtain the equation of regression to be as follows,

 

 Notations: LB-low budget, MB-medium budget, HB-high budget, RMM-Rajiv Masand

medium rating, RMH-Rajiv Masand high rating, TOIM-Times of India medium rating,

Page 19: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 19/30

TOIH-Times of India high rating, IS-Item songs, UA-Universal/Adult, PH-famous

 production house, FES-festival proximity, STRY-original story, STAR-famous stars

 presence, PROMO-use of special promotion tactics, MSC-success of music release and

CNTR-controversies in movie making and release.

The expected firstweek sales can now be computed using the following scale table for the

QuickRate value, which can be either scaled for value, or rounded off to nearest integer, for a

fair estimate.

QuickRate score First Week Revenue multiplier 

5 or less < 1 times

6 1-1.2 times

7 1.2-1.75 times

8 1.75-2.25 times

9 2.25-3 times

10 3+ times

And thus  

 Now we shall proceed to use this fair estimate of the FirstWeek Sales revenue and perform

regression for viewer opinion and gross sales revenue, at continuum. The new variables

added would be, FWM-low first week sales, FWH-high first week sales, proxy used is

RevScore, which is the revenue scaled to out of 10.

 

 Now based on our conjoint analysis for the evaluating the gross revenue that can be collected

over the tenure of the movie at box office the following regression equation was found,

Page 20: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 20/30

 This revenue score RevScore can then be scaled using the following table to evalute the

expected gross revenue.

RevScore Gross Revenue multiplier 

5 or less Max 1.5 times

6 1.5 - 2 times

7 2 – 2.5 times

8 2.5 – 3.5 times

9 3.5 - 4.5 times

10 4.5 + times

The gross revenue can be estimated by  

To the last part of our analysis, apart from the gross sales and intial sales, what matters is thatthe movie should resound in viewer‟s mind, which is usually meared by rating movies

themselves, as in, movies which are highly regarded by viewers will be seen again and again,

or even through sale of movie dvd or online copies, which again add to revenue of production

house. This is measured by a proxy called Score, for viewer‟s opinion. 

 

Upon cojoint analysis, we arrive at the equation,

 

Page 21: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 21/30

Cluster Analysis

Heirarchical cluster , using Ward‟s method, was performed, and we found a sudden jump in

the value of coefficient at stage 55, which indicates, that we must consider 58-55=3 clusters.

Agglomeration Schedule 

Stage Cluster Combined Coefficients Stage Cluster First Appears NextStageCluster 1 Cluster 2 Cluster 1 Cluster 2

1 11 53 1.000 0 0 72 15 28 2.000 0 0 153 12 17 3.000 0 0 204 36 55 4.500 0 0 34

5 7 32 6.000 0 0 16

6 14 26 7.500 0 0 8

7 11 19 9.167 1 0 17

8 8 14 11.000 0 6 24

9 40 54 13.000 0 0 3910 21 47 15.000 0 0 23

11 13 31 17.000 0 0 14

12 20 27 19.000 0 0 18

13 2 38 21.500 0 0 37

14 13 30 24.167 11 0 36

15 15 33 27.167 2 0 24

16 3 7 30.333 0 5 3317 11 25 33.667 7 0 25

18 20 22 37.000 12 0 42

19 43 48 40.500 0 0 34

20 12 59 44.167 3 0 37

21 9 57 48.167 0 0 31

22 6 49 52.167 0 0 4223 21 42 56.167 10 0 30

24 8 15 60.333 8 15 38

25 5 11 64.733 0 17 36

26 45 46 69.233 0 0 50

27 29 37 73.733 0 0 43

28 16 23 78.233 0 0 45

29 39 52 83.733 0 0 4730 18 21 89.233 0 23 35

31 9 50 95.233 21 0 48

32 4 34 101.233 0 0 40

33 3 56 107.567 16 0 51

34 36 43 114.067 4 19 5035 18 44 120.967 30 0 45

36 5 13 128.150 25 14 46

37 2 12 136.183 13 20 4138 8 24 144.398 24 0 49

39 40 51 153.064 9 0 43

40 4 10 161.731 32 0 48

41 2 35 171.031 37 0 44

42 6 20 180.898 22 18 4743 29 40 191.331 27 39 54

44 2 41 201.974 41 0 54

45 16 18 212.788 28 35 52

46 5 58 226.094 36 0 49

47 6 39 240.537 42 29 5248 4 9 256.870 40 31 51

Page 22: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 22/30

49 5 8 275.663 46 38 55

50 36 45 297.496 34 26 53

51 3 4 320.896 33 48 55

52 6 16 345.610 47 45 53

53 6 36 382.655 52 50 56

54 2 29 420.329 44 43 57

55 3 5 460.059 51 49 5656 3 6 506.112 55 53 57

57 2 3 598.431 54 56 0

 Now, we proceed to perform the K-means cluster analysis, to determin the smaples in each

cluster, and the distances between the clusters. The result of K-means clustering is as follow

Final Cluster Centers 

Cluster 

1 2 3

Star-cast influence 4 4 3

Production house 3 4 2

Director influence 3 4 4

Music Influence 4 3 3

Item Songs 3 2 2

Review influence 3 2 3

Indifference to

rating3 2 3

Controversies 4 2 2

 A-rating 3 3 2

ANOVA 

Cluster Error F Sig.

Mean Square df Mean Square df 

Star-cast influence 5.753 2 .678 55 8.490 .001

Production house 24.164 2 .630 55 38.351 .000Director influence 6.610 2 .683 55 9.681 .000

Music Influence 3.002 2 .844 55 3.557 .035

Item Songs 17.795 2 .744 55 23.924 .000

Review influence 3.748 2 1.209 55 3.100 .053

Indifference to rating 1.006 2 .878 55 1.146 .325

Controversies 15.887 2 1.051 55 15.115 .000

 A-rating 4.596 2 1.162 55 3.956 .025

The F tests should be used only for descriptive purposes because the clusters have been

chosen to maximize the differences among cases in different clusters. The observedsignificance levels are not corrected for this and thus cannot be interpreted as tests of the

hypothesis that the cluster means are equal.

Number of Cases in each

Cluster  

Cluster 

1 24.000

2 21.000

3 13.000

Valid 58.000

Missing .000

Page 23: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 23/30

Cluster 1: Segment which is drawn by star-cast, music, and controversies, in short, the page-3

readers of national dailies, and seem young and full of energy.

Cluster 2: Segment which is drawn by as much by the director and star-cast, music and are

indifferent to critic review

Cluster 3: Segment which goes to watch and enjoy, movies, usually with family, and prefer a

wholesome movie, with good story, stars, and less controversies or parental-guidance needs.

Page 24: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 24/30

When comparing the three clusters within themselves, we come to a conclusion that, the three

clusters are diverse within themselves

ANOVA 

Sum of 

Squares

df Mean

Square

F Sig.

Star-cast

influence

Between

Groups18.647 2 9.324 17.021 .000

Within Groups 30.128 55 .548

Total 48.776 57

Review

influence

Between

Groups36.698 2 18.349 27.054 .000

Within Groups 37.302 55 .678

Total 74.000 57

Music

Influence

Between

Groups23.369 2 11.685 22.114 .000

Within Groups 29.062 55 .528

Total 52.431 57

Thus we conclude that, the clustering of respondents was successful, and must be replicated

for a larger sample of respondents, with more demographic variables.

Page 25: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 25/30

Discussion

1.  From the above descriptive analysis, we can infer that, a majority of the sample,

assuming it to be a representative of the population, is of a gossip-driven generation,and is interested in movies, that can provide with the „tadka‟ for spending time.

2.  The aim of the focus group discussion was to first identify the gamut of factors that

could possibly influence the decision of the people to go and watch a movie, once, or 

maybe even multiple number of times. Based on the findings of the FGD, the

independent variables were listed down.

3.  Many moviegoers are driven by the special promotion activities and the television

coverage, they seek.

4.  The review of critics and peer-to-peer rating also plays a crucial role, which can be

seen by way of the linear coefficient in the regression equation.

5.  From the focus-group discussions, it became clear that, most people preferred to wait

for the reviews and then go watch it.

6.  By way of questionnaire, we could confirm that, off-late the trend for movie making

is shifting from originality of content, to roping in elite stars, and putting together an

item number, and paying big bucks to reserve lot many screens, to push the movie in

cinema halls.

7.  While collecting the data from theatre going crowd, through card-samples, we noticed

the willingness of the moviegoers to contribute in every possible way, to help make

the movie watching experience better.

8.  From the literature review, it came to our notice that, most film-makers were now

shifting focus, from innovative stories, and directions, to making sequels of a already

established brand, thus handing over to new script writers, a better chance of 

succeeding even with a low budget movie.

9.  Secondary data collection revealed the variety of ways used by film producers to push

the film into cinema halls, and bring larger crowd to see it and break even.

10.  The simple linear regression failed to reveal the hidden tendency of the gross revenue

and viewer opinion‟s variation with respect to the critic rating, which was better 

explained in dummy variable regression in Conjoint Analysis.

11.  The dummy variable regression for conjoint analysis of the said modeling, gave us

some interesting insights. Rajiv Masand‟s critique of a movie, as more severe impact,

Page 26: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 26/30

when it is low than when it is high or medium, which confirms the prospect theory.

Similarly, the most impact is for a high rating from the Times of India.

12.  Factor analysis could not be performed due to the fact that the sample size was too

small and coherent in many ways. Instead, the cluster sampling allowed us to segment

the potential market and reduce our vision to a select target segment, which had fair 

majority stake in the market.

13.  Three levels of conjoint analysis have been performed. First based on the producer 

and director‟s judgment on what kind of movie could be made, we propose the first

level of regression, i.e. estimation of the first week sales of the movie. Based on the

multiplier effect, the first week sales can be again scaled to low, medium or high, and

again used in second level of regression, i.e. user opinion score and also for the third

level, parallel to second, for the estimation of the gross earnings of the movie, again

first evaluated as a score and then multiplied to obtain the expected earnings.

Page 27: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 27/30

Limitations of the Study

1.  We were able to conduct only one insightful focus group discussion, even after three

sittings, which has led to some eastage of time, energy and valuable analysis2.  The assorted questionnaire was distributed through social networking sites like the

Facebook and twitter. Hence this mode of convenience sampling has not covered all

aspects of demographic variables, due to which factor analysis failed.

3.  To some extent, the survey respondents provided skewed responses, because most

were from one particular area of India, or from certain lifestyle, with preconceived

notions and tastes and preferences.

4.  The sample of movies collected for performing conjoint analysis was only 74, which

is very small, to have an accurate model and significance. Similarly the survey

responses were too small in numbers, for any hard conclusive inferences.

5.  Detailed cluster analysis could not be performed as respondent were mainly from the

within an age group of 20 to 26.

6.  On account of constraints on time and efficiency, we could not incorporate the details

for movies starting from 2005, which witnessed the shift in Bollywood paradigm.

7.  Most respondents refrained from giving a perfect score to films due to the inherent

 bias, of having seen a better film, or out of stigma, of being considered as a person of 

 poor taste in movies.

Future Research

1.  With further inputs and historical aggregation of data, from all possible movies, it

should be possible to model a better and more accurate system, with dynamic data

handling and updating capabilities.2.  Further the time value of money needs to be taken into consideration when looking at

revenues earned by the film-makers

3.  Trends in viewer behaviors have to be monitored and analyzed, for propor modeling

 by integration of movies across the horizon.

4.  Better questionnaire tapping into demographic variables and additional independent

variables will help to create more reasonable, accurate and sustainable model, with

much larger scope than just predicting, but also tracking variable changes and their 

effects.

Page 28: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 28/30

Works Cited

Fetscherin, Marc, The Main Determinants of Bollywood Movie Box Office Sales ,  Journal of 

Global Marketing, 23:5, 461-476.

Wallace, W., Seigerman, A., Holbrook, M. (1993), The role of actors and actresses in the

success of films: How much is a movie star worth? Journal of Cultural Economics, 17(1), 1 – 

27.

Sood, S. & Dreze, X. (2006). Brand Extensions of Experiential Goods: Movie Sequel

Evaluations, Journal of Consumer Research, 33(December), 352-360.

Sawhney, M. & Eliashberg, J. (1996). A Parsimonious Model for Forecasting gross Box-

Office revenues of Motion Picture, Management Science, 15(2), 113-131.

Eliashberg, J. & Shugan, S. (1997). Film critics: Influencers or predictors?  Journal of 

 Marketing , 61, 68-78.

DeVany, A. & Walls, D. (1999). Uncertainty in the Movie Industry: Does Star Power Reduce

the Terror of the Box Office?, Journal of Cultural Economics, 23(4), 285- 318.

 Naresh Malhotra, Satyabhushan Dash,  Marketing Research-An Applied Orientation, 6

th

 Edition, ISBN-978-81-317-3181-9

Schwartz, J. B. (2011). What drives immediate and ongoing word of mouth?  Journal of 

 Marketing research 

Bagella, M. & Becchetti, L. (1999). The Determinants of Motion Picture Box Office

Performance: Evidence from Movies Produced in Italy.  Journal of Cultural Economics,

23(4), 237-256.

Chang, B-H. & Ki, E-J. (2005). Devising a Practical Model for Predicting Theatrical Movie

Success: Focusing on the Experience Good Property.  Journal of Media Economics, 18(4),

247-269.

Page 29: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 29/30

Appendix

Questionnaire

Page 30: A3 Bollywood Movies

7/28/2019 A3 Bollywood Movies

http://slidepdf.com/reader/full/a3-bollywood-movies 30/30

 

Card for dummy variable analysis