In this initial analysis, a cleaned subset of the TMDB dataset from https://www.kaggle.com/tmdb/tmdb-movie-metadata is used.

We analyse the different dependent and independent variables present in order to hypothesize and find patterns between data.

Cleaning the dataset

tmdb<-read.csv('C:\\Users\\ADI\\Downloads\\tmdb_5000_movies.csv',header=T,sep=",",stringsAsFactors = F)
tmdb<-tmdb[complete.cases(tmdb),]
tmdb<-tmdb[tmdb$budget!=0,]
tmdb<-tmdb[tmdb$revenue!=0,]
tmdb<-cbind(tmdb[,c(1,2,4,6,9,12,13,14,15,18,19,20)])
tmdb<-tmdb[c(1:3030,3032:nrow(tmdb)),]

Extracting genre data from json string

for (i in 1:nrow(tmdb)){
  kek<-fromJSON(tmdb$genres[i])
  for (j in 1:nrow(kek[2])){
    tmdb[i,kek[,2][j]]=1
  }
}
tmdb[is.na(tmdb)]<-0
tmdb<-tmdb[-c(2,9)]

Visualising the length and breadth of the dataset.

plot(tmdb$revenue/10^6 ~ as.Date(tmdb$release_date),data=tmdb,ylab="Revenue (Million USD)", xlab="Release date",main="Visualisation of the dataset")

Descriptive statistics.

kable(describe(tmdb))

## Warning in describe(tmdb): NAs introduced by coercion

## Warning in describe(tmdb): NAs introduced by coercion

## Warning in describe(tmdb): NAs introduced by coercion

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning
## Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning
## Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to max; returning
## -Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to max; returning
## -Inf

	vars	n	mean	sd	median	trimmed	mad	min	max	range	skew	kurtosis	se
budget	1	3228	4.066642e+07	4.439840e+07	2.500000e+07	3.223486e+07	2.742810e+07	1.000000	3.800000e+08	3.800000e+08	2.0874924	5.5103834	7.814489e+05
id	2	3228	4.477959e+04	7.462097e+04	1.144650e+04	2.524563e+04	1.486603e+04	5.000000	4.178590e+05	4.178540e+05	2.3702084	4.9185428	1.313391e+03
original_language*	3	3228	NaN	NA	NA	NaN	NA	Inf	-Inf	-Inf	NA	NA	NA
popularity	4	3228	2.904267e+01	3.616773e+01	2.041296e+01	2.366746e+01	1.787573e+01	0.019984	8.755813e+02	8.755613e+02	9.2578808	162.4783998	6.365822e-01
release_date*	5	3228	NaN	NA	NA	NaN	NA	Inf	-Inf	-Inf	NA	NA	NA
revenue	6	3228	1.212800e+08	1.863198e+08	5.519150e+07	8.061051e+07	6.878759e+07	5.000000	2.787965e+09	2.787965e+09	3.8161677	24.8492115	3.279384e+06
runtime	7	3228	1.107215e+02	2.096831e+01	1.070000e+02	1.084652e+02	1.779120e+01	41.000000	3.380000e+02	2.970000e+02	1.6932466	7.3879771	3.690597e-01
title*	8	3228	9.744000e+02	9.566594e+02	8.540000e+02	9.611250e+02	1.243901e+03	9.000000	2.046000e+03	2.037000e+03	0.0560208	-2.1009033	1.683800e+01
vote_average	9	3228	6.309758e+00	8.737225e-01	6.300000e+00	6.341022e+00	8.895600e-01	0.000000	8.500000e+00	8.500000e+00	-0.6084960	1.9475113	1.537820e-02
vote_count	10	3228	9.775895e+02	1.414424e+03	4.710000e+02	6.639443e+02	5.396664e+02	0.000000	1.375200e+04	1.375200e+04	3.2042773	13.8899767	2.489505e+01
Action	11	3228	2.843866e-01	4.511917e-01	0.000000e+00	2.306502e-01	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	0.9554546	-1.0874431	7.941300e-03
Adventure	12	3228	2.047708e-01	4.035965e-01	0.000000e+00	1.311920e-01	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	1.4625388	0.1390631	7.103600e-03
Fantasy	13	3228	1.059480e-01	3.078187e-01	0.000000e+00	7.739900e-03	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	2.5594936	4.5524181	5.417900e-03
Science Fiction	14	3228	1.335192e-01	3.401877e-01	0.000000e+00	4.218270e-02	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	2.1539124	2.6401567	5.987600e-03
Crime	15	3228	1.614002e-01	3.679567e-01	0.000000e+00	7.701240e-02	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	1.8398623	1.3855229	6.476300e-03
Drama	16	3228	4.464064e-01	4.971965e-01	0.000000e+00	4.330495e-01	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	0.2155162	-1.9541578	8.751100e-03
Thriller	17	3228	2.896530e-01	4.536716e-01	0.000000e+00	2.372291e-01	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	0.9270221	-1.1409832	7.985000e-03
Animation	18	3228	5.824040e-02	2.342337e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	3.7707867	12.2226189	4.122700e-03
Family	19	3228	1.130731e-01	3.167312e-01	0.000000e+00	1.664090e-02	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	2.4424939	3.9670056	5.574700e-03
Western	20	3228	1.765800e-02	1.317253e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	7.3211823	51.6156999	2.318500e-03
Comedy	21	3228	3.438662e-01	4.750707e-01	0.000000e+00	3.049536e-01	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	0.6571042	-1.5686998	8.361600e-03
Romance	22	3228	1.778191e-01	3.824196e-01	0.000000e+00	9.752320e-02	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	1.6844382	0.8375919	6.730900e-03
Horror	23	3228	1.028501e-01	3.038100e-01	0.000000e+00	3.870000e-03	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	2.6136526	4.8326772	5.347300e-03
Mystery	24	3228	8.209420e-02	2.745507e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	3.0433461	7.2642060	4.832300e-03
History	25	3228	4.491950e-02	2.071593e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	4.3921705	17.2965199	3.646200e-03
War	26	3228	3.717470e-02	1.892191e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	4.8904365	21.9231610	3.330400e-03
Music	27	3228	3.438660e-02	1.822484e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	5.1080748	24.0998939	3.207700e-03
Documentary	28	3228	1.177200e-02	1.078750e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	9.0489300	79.9078888	1.898700e-03
Foreign	29	3228	1.548900e-03	3.933230e-02	0.000000e+00	0.000000e+00	0.000000e+00	0.000000	1.000000e+00	1.000000e+00	25.3378082	640.2028513	6.923000e-04

Creating a few more categorical variables

is_profit=ifelse((tmdb$revenue-tmdb$budget)>0,1,0)
#1:film resulted in net profit
season_no<-ifelse(month(as.Date(tmdb$release_date)) %in% seq(3,5),1,ifelse(month(as.Date(tmdb$release_date)) %in% seq(6,8),2,ifelse(month(as.Date(tmdb$release_date)) %in% seq(9,11),3,ifelse(month(as.Date(tmdb$release_date)) %in% c(1,2,12),4,0))))
for(i in 1:nrow(tmdb)){
tmdb[i,"is_niche"]<-ifelse(sum(tmdb[i,c(11:14,17:19,21:23)]),0,1)
}
#1=spring,2=summer,3=fall,4=winter
tmdb<-cbind(tmdb,is_profit,season_no)

Contingency tables

One way tables:

addmargins(table(tmdb$season_no))

## 
##    1    2    3    4  Sum 
##  704  837  933  754 3228

addmargins(table(tmdb$is_profit))

## 
##    0    1  Sum 
##  790 2438 3228

addmargins(xtabs(~season_no+Action,data=tmdb))

##          Action
## season_no    0    1  Sum
##       1    476  228  704
##       2    548  289  837
##       3    721  212  933
##       4    565  189  754
##       Sum 2310  918 3228

addmargins(xtabs(~is_profit+Fantasy,data=tmdb))

##          Fantasy
## is_profit    0    1  Sum
##       0    723   67  790
##       1   2163  275 2438
##       Sum 2886  342 3228

Boxplots of variables important to the study.

par(mfrow=c(1,2))
boxplot(tmdb$revenue,ylab="revenue")
boxplot(tmdb$popularity,ylab="popularity")

Histograms of suitable data fields.

par(mfrow=c(2,1))
hist(tmdb$season_no)
hist(tmdb$vote_average)

Suitable plots.

par(mfrow=c(2,3))
plot(tmdb$revenue,tmdb$budget)
plot(tmdb$revenue,tmdb$vote_average)
plot(tmdb$revenue,tmdb$popularity)
plot(tmdb$season_no,tmdb$revenue)
plot(as.Date(tmdb$release_date),tmdb$revenue)
plot(as.Date(tmdb$release_date),tmdb$popularity)

Correlation matrix (rounded to 2 decimal places)

kek<-cbind(tmdb[,c(1,4,6,7,9,10:32)])
kable(round(cor(kek, use="complete.obs", method="kendall"),2))

	budget	popularity	revenue	runtime	vote_average	vote_count	Action	Adventure	Fantasy	Science Fiction	Crime	Drama	Thriller	Animation	Family	Western	Comedy	Romance	Horror	Mystery	History	War	Music	Documentary	Foreign	is_niche	is_profit	season_no
budget	1.00	0.33	0.50	0.17	-0.09	0.34	0.24	0.28	0.19	0.13	-0.01	-0.16	0.05	0.17	0.18	-0.03	-0.02	-0.09	-0.15	0.02	0.00	0.01	-0.06	-0.11	-0.05	-0.16	0.04	-0.05
popularity	0.33	1.00	0.52	0.14	0.23	0.82	0.13	0.17	0.14	0.11	0.02	-0.12	0.07	0.11	0.06	-0.03	-0.09	-0.10	-0.01	0.04	-0.05	0.00	-0.07	-0.11	-0.05	-0.11	0.34	-0.04
revenue	0.50	0.52	1.00	0.16	0.09	0.56	0.15	0.23	0.15	0.08	-0.04	-0.17	0.01	0.15	0.17	-0.06	0.00	-0.05	-0.06	0.00	-0.02	-0.01	-0.03	-0.08	-0.05	-0.14	0.47	-0.05
runtime	0.17	0.14	0.16	1.00	0.27	0.14	0.08	0.07	-0.02	0.00	0.05	0.27	0.03	-0.22	-0.20	0.05	-0.27	0.04	-0.17	0.04	0.19	0.15	0.00	-0.05	-0.03	0.19	0.05	0.02
vote_average	-0.09	0.23	0.09	0.27	1.00	0.25	-0.11	-0.04	-0.05	-0.05	0.05	0.26	-0.08	0.04	-0.04	0.05	-0.17	0.02	-0.14	0.01	0.11	0.09	0.04	0.06	0.00	0.22	0.19	0.03
vote_count	0.34	0.82	0.56	0.14	0.25	1.00	0.13	0.17	0.14	0.13	0.02	-0.13	0.06	0.09	0.06	-0.04	-0.07	-0.09	0.00	0.03	-0.05	-0.01	-0.08	-0.10	-0.05	-0.12	0.36	-0.04
Action	0.24	0.13	0.15	0.08	-0.11	0.13	1.00	0.36	0.07	0.25	0.14	-0.24	0.29	-0.09	-0.12	0.04	-0.19	-0.22	-0.08	-0.06	0.00	0.05	-0.09	-0.06	-0.02	-0.24	0.00	-0.08
Adventure	0.28	0.17	0.23	0.07	-0.04	0.17	0.36	1.00	0.24	0.23	-0.13	-0.26	-0.01	0.19	0.23	0.03	-0.07	-0.14	-0.13	-0.07	-0.03	0.01	-0.07	-0.06	-0.02	-0.20	0.05	-0.08
Fantasy	0.19	0.14	0.15	-0.02	-0.05	0.14	0.07	0.24	1.00	0.05	-0.13	-0.16	-0.11	0.12	0.27	-0.03	0.02	-0.03	0.01	-0.04	-0.07	-0.05	-0.02	-0.04	-0.01	-0.13	0.04	-0.04
Science Fiction	0.13	0.11	0.08	0.00	-0.05	0.13	0.25	0.23	0.05	1.00	-0.13	-0.22	0.10	-0.02	-0.01	-0.05	-0.14	-0.13	0.07	0.01	-0.09	-0.07	-0.07	-0.04	-0.02	-0.15	0.01	-0.09
Crime	-0.01	0.02	-0.04	0.05	0.05	0.02	0.14	-0.13	-0.13	-0.13	1.00	0.07	0.30	-0.11	-0.15	-0.01	-0.09	-0.13	-0.08	0.13	-0.06	-0.08	-0.06	-0.05	-0.02	-0.01	-0.01	0.03
Drama	-0.16	-0.12	-0.17	0.27	0.26	-0.13	-0.24	-0.26	-0.16	-0.22	0.07	1.00	-0.04	-0.19	-0.20	-0.01	-0.23	0.20	-0.19	0.03	0.20	0.14	0.05	-0.09	0.01	0.33	-0.10	0.11
Thriller	0.05	0.07	0.01	0.03	-0.08	0.06	0.29	-0.01	-0.11	0.10	0.30	-0.04	1.00	-0.15	-0.22	-0.06	-0.37	-0.22	0.21	0.25	-0.08	-0.05	-0.11	-0.07	-0.03	-0.25	-0.01	-0.01
Animation	0.17	0.11	0.15	-0.22	0.04	0.09	-0.09	0.19	0.12	-0.02	-0.11	-0.19	-0.15	1.00	0.60	-0.01	0.11	-0.09	-0.08	-0.07	-0.05	-0.04	0.03	-0.03	0.02	-0.10	0.03	-0.02
Family	0.18	0.06	0.17	-0.20	-0.04	0.06	-0.12	0.23	0.27	-0.01	-0.15	-0.20	-0.22	0.60	1.00	-0.03	0.19	-0.08	-0.12	-0.10	-0.08	-0.07	0.06	-0.01	0.04	-0.14	0.05	-0.04
Western	-0.03	-0.03	-0.06	0.05	0.05	-0.04	0.04	0.03	-0.03	-0.05	-0.01	-0.01	-0.06	-0.01	-0.03	1.00	-0.05	-0.03	-0.05	-0.02	0.03	0.01	0.01	-0.01	-0.01	0.11	-0.02	-0.01
Comedy	-0.02	-0.09	0.00	-0.27	-0.17	-0.07	-0.19	-0.07	0.02	-0.14	-0.09	-0.23	-0.37	0.11	0.19	-0.05	1.00	0.19	-0.16	-0.17	-0.14	-0.12	0.03	-0.05	-0.01	-0.28	0.01	-0.03
Romance	-0.09	-0.10	-0.05	0.04	0.02	-0.09	-0.22	-0.14	-0.03	-0.13	-0.13	0.20	-0.22	-0.09	-0.08	-0.03	0.19	1.00	-0.13	-0.07	-0.02	0.00	0.12	-0.05	0.02	-0.18	0.01	0.02
Horror	-0.15	-0.01	-0.06	-0.17	-0.14	0.00	-0.08	-0.13	0.01	0.07	-0.08	-0.19	0.21	-0.08	-0.12	-0.05	-0.16	-0.13	1.00	0.15	-0.07	-0.06	-0.06	-0.04	-0.01	-0.13	0.05	0.00
Mystery	0.02	0.04	0.00	0.04	0.01	0.03	-0.06	-0.07	-0.04	0.01	0.13	0.03	0.25	-0.07	-0.10	-0.02	-0.17	-0.07	0.15	1.00	-0.05	-0.04	-0.05	-0.03	-0.01	-0.05	-0.02	0.00
History	0.00	-0.05	-0.02	0.19	0.11	-0.05	0.00	-0.03	-0.07	-0.09	-0.06	0.20	-0.08	-0.05	-0.08	0.03	-0.14	-0.02	-0.07	-0.05	1.00	0.31	-0.01	0.02	-0.01	0.22	-0.03	0.07
War	0.01	0.00	-0.01	0.15	0.09	-0.01	0.05	0.01	-0.05	-0.07	-0.08	0.14	-0.05	-0.04	-0.07	0.01	-0.12	0.00	-0.06	-0.04	0.31	1.00	-0.03	-0.02	-0.01	0.10	-0.02	0.04
Music	-0.06	-0.07	-0.03	0.00	0.04	-0.08	-0.09	-0.07	-0.02	-0.07	-0.06	0.05	-0.11	0.03	0.06	0.01	0.03	0.12	-0.06	-0.05	-0.01	-0.03	1.00	0.09	-0.01	0.06	0.00	0.02
Documentary	-0.11	-0.11	-0.08	-0.05	0.06	-0.10	-0.06	-0.06	-0.04	-0.04	-0.05	-0.09	-0.07	-0.03	-0.01	-0.01	-0.05	-0.05	-0.04	-0.03	0.02	-0.02	0.09	1.00	0.07	0.22	-0.01	0.02
Foreign	-0.05	-0.05	-0.05	-0.03	0.00	-0.05	-0.02	-0.02	-0.01	-0.02	-0.02	0.01	-0.03	0.02	0.04	-0.01	-0.01	0.02	-0.01	-0.01	-0.01	-0.01	-0.01	0.07	1.00	0.01	-0.07	0.01
is_niche	-0.16	-0.11	-0.14	0.19	0.22	-0.12	-0.24	-0.20	-0.13	-0.15	-0.01	0.33	-0.25	-0.10	-0.14	0.11	-0.28	-0.18	-0.13	-0.05	0.22	0.10	0.06	0.22	0.01	1.00	-0.05	0.08
is_profit	0.04	0.34	0.47	0.05	0.19	0.36	0.00	0.05	0.04	0.01	-0.01	-0.10	-0.01	0.03	0.05	-0.02	0.01	0.01	0.05	-0.02	-0.03	-0.02	0.00	-0.01	-0.07	-0.05	1.00	-0.03
season_no	-0.05	-0.04	-0.05	0.02	0.03	-0.04	-0.08	-0.08	-0.04	-0.09	0.03	0.11	-0.01	-0.02	-0.04	-0.01	-0.03	0.02	0.00	0.00	0.07	0.04	0.02	0.02	0.01	0.08	-0.03	1.00

Corrgram

corrgram(tmdb, order=TRUE, lower.panel=panel.shade,
  upper.panel=panel.pie, text.panel=panel.txt,
  diag.panel=panel.minmax, 
    main="Corrgram")

Scatterplot matrix

pairs(kek[,c(1:6,27)])

Hypothesis testing:

Hypothesis 1-

H0:There is no significant revenue difference across release seasons for films. H1:There is a significant revenue difference across release seasons for films.

t.test(tmdb$season_no,tmdb$revenue)

## 
##  Welch Two Sample t-test
## 
## data:  tmdb$season_no and tmdb$revenue
## t = -36.983, df = 3227, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -127709883 -114850109
## sample estimates:
##    mean of x    mean of y 
## 2.538104e+00 1.212800e+08

Due to very low p value we reject the null hypothesis.

Hypothesis 2-

H0:Average scores of a movie are significantly independent of whether a movie is niche or mainstream H1:Average scores of a movie are significantly dependent on whether a movie is niche or mainstream

  t.test(tmdb$vote_average,tmdb$is_niche)

## 
##  Welch Two Sample t-test
## 
## data:  tmdb$vote_average and tmdb$is_niche
## t = 375.27, df = 4156.3, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  6.148595 6.213177
## sample estimates:
## mean of x mean of y 
## 6.3097584 0.1288724

Due to very low p value we reject the null hypothesis.

Regression analysis:

Model1- revenue=b0+b1(budget)+b2(season)+b3(average_votes)+b4(popularity)

reg<-lm(revenue~ budget+season_no+vote_average+popularity, tmdb)
summary(reg)

## 
## Call:
## lm(formula = revenue ~ budget + season_no + vote_average + popularity, 
##     data = tmdb)
## 
## Residuals:
##        Min         1Q     Median         3Q        Max 
## -942315694  -48463108   -8457926   28342093 1982127522 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  -1.659e+08  1.618e+07 -10.253   <2e-16 ***
## budget        2.378e+00  5.167e-02  46.017   <2e-16 ***
## season_no    -4.251e+06  1.901e+06  -2.236   0.0254 *  
## vote_average  2.423e+07  2.464e+06   9.830   <2e-16 ***
## popularity    1.667e+06  6.594e+04  25.285   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 115200000 on 3223 degrees of freedom
## Multiple R-squared:  0.6182, Adjusted R-squared:  0.6178 
## F-statistic:  1305 on 4 and 3223 DF,  p-value: < 2.2e-16

revenue=(-1.739e+08)+(2.386e+00)(budget)+(-1.234e+06)(season)+(2.416e+07)(average_votes)+(1.669e+06)(popularity)

Model2- We observe in previous model that season_no is not a statistically significant variable (it does not have *, has a high p-value) Thus we generate a new model for revenue, which is best fit

reg1<-lm(revenue~ budget+vote_average+popularity, tmdb)
summary(reg1)

## 
## Call:
## lm(formula = revenue ~ budget + vote_average + popularity, data = tmdb)
## 
## Residuals:
##        Min         1Q     Median         3Q        Max 
## -947047990  -47963423   -8101178   28799282 1973822993 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  -1.759e+08  1.556e+07 -11.304   <2e-16 ***
## budget        2.387e+00  5.151e-02  46.348   <2e-16 ***
## vote_average  2.402e+07  2.464e+06   9.748   <2e-16 ***
## popularity    1.670e+06  6.597e+04  25.315   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 115300000 on 3224 degrees of freedom
## Multiple R-squared:  0.6176, Adjusted R-squared:  0.6173 
## F-statistic:  1736 on 3 and 3224 DF,  p-value: < 2.2e-16

plot(reg1)

revenue=(-1.759e+08)+( 2.387e+00)(budget)+(2.402e+07)(average_votes)+(1.670e+06)(popularity)

This model is the best fit model since all variables are statistically significant and Multiple R squared value indicates that this is a good model.

Model3- average_votes=b0+b1(duration)+b2(budget)+b3(mainstream)

reg2<-lm(vote_average~ budget+ runtime+ !is_niche, tmdb)
summary(reg2)

## 
## Call:
## lm(formula = vote_average ~ budget + runtime + (!is_niche), data = tmdb)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -6.9184 -0.4643  0.0305  0.5145  2.3854 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    4.978e+00  9.456e-02  52.640  < 2e-16 ***
## budget        -1.865e-09  3.325e-10  -5.609 2.21e-08 ***
## runtime        1.543e-02  7.133e-04  21.637  < 2e-16 ***
## !is_nicheTRUE -3.454e-01  4.405e-02  -7.841 6.04e-15 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.7943 on 3224 degrees of freedom
## Multiple R-squared:  0.1742, Adjusted R-squared:  0.1735 
## F-statistic: 226.8 on 3 and 3224 DF,  p-value: < 2.2e-16

plot(reg2)

average_votes=(4.978)+(1.543e-0)2(runtime)+(-1.865e-09)(budget)+-3.454e-01(mainstream)

This model is the best fit model since all variables are statistically significant and Multiple R squared value indicates that this is a good model.

Insights from regression analysis- 1)The revenue of a film significantly depends upon its budget,popularity and average votes 2)The average votes earned by a film significantly depends on its budget, runtime, whether its genre is mainstream/niche