Analysis of Cryptocurrency
Soumyadeep Sengupta
Project on Cryptocurrency
1. Introduction
A cryptocurrency (or crypto currency) is a digital asset designed to work as a medium of exchange that uses cryptography to secure its transactions, to control the creation of additional units, and to verify the transfer of assets. Cryptocurrencies are classified as a subset of digital currencies and are also classified as a subset of alternative currencies and virtual currencies. Cryptocurrencies use decentralized control as opposed to centralized electronic money and central banking systems. The decentralized control of each cryptocurrency works through a blockchain, which is a public transaction database, functioning as a distributed ledger.
2.Over view of Study
The dataset is a combination of all the different types of currencies. Here we have mentioned all the currencies value according values of bits coin and also mentioned their values according to USd. We also mentioned the growth of each currencies in 1hr ,24hrs and in 7days. these will help to measure the continuous ups and downs of their value.
3. An empirical field study of Cryptocurrency in all over the world.
Decentralized cryptocurrency is produced by the entire cryptocurrency system collectively, at a rate which is defined when the system is created and which is publicly known. In centralized banking and economic systems such as the Federal Reserve System, corporate boards or governments control the supply of currency by printing units of fiat money or demanding additions to digital banking ledgers. In case of decentralized cryptocurrency, companies or governments cannot produce new units, and have not so far provided backing for other firms, banks or corporate entities which hold asset value measured in it. The underlying technical system upon which decentralized cryptocurrencies are based was created by the group or individual known as Satoshi Nakamoto.
As of September 2017, over a thousand cryptocurrency specifications exist; most are similar to and derive from the first fully implemented decentralized cryptocurrency, bitcoin. Within cryptocurrency systems the safety, integrity and balance of ledgers is maintained by a community of mutually distrustful parties referred to as miners: members of the general public using their computers to help validate and timestamp transactions, adding them to the ledger in accordance with a particular timestamping scheme.Miners have a financial incentive to maintain the security of a cryptocurrency ledger.
Most cryptocurrencies are designed to gradually decrease production of currency, placing an ultimate cap on the total amount of currency that will ever be in circulation, mimicking precious metals. Compared with ordinary currencies held by financial institutions or kept as cash on hand, cryptocurrencies can be more difficult for seizure by law enforcement. This difficulty is derived from leveraging cryptographic technologies.
a.Overview
This project will deal with variation of the values of each currencies . If we prove that we can accept the hypothesis we can predict the variation and can predict the ups and downs .
b.Hypothesis
\[ Variation=\alpha 0+\alpha1percent_change_1h+\alpha2percent_change_24h+\alpha3percent_change_7days+e \]
c. Information related Data
Parameters and meanings of their are showed in Cryptocurrency dataset
d. Data:
crypto.df <- read.csv(paste("cryptocurrencies_prices.csv", sep=""), stringsAsFactors=FALSE)
head(crypto.df)## X id name symbol rank price_usd price_btc
## 1 1 bitcoin Bitcoin BTC 1 1.34813e+04 1.00000000
## 2 2 ripple Ripple XRP 2 2.29933e+00 0.00017157
## 3 3 ethereum Ethereum ETH 3 8.81320e+02 0.06576140
## 4 4 bitcoin-cash Bitcoin Cash BCH 4 2.44816e+03 0.18267400
## 5 5 cardano Cardano ADA 5 7.05031e-01 0.00005261
## 6 6 litecoin Litecoin LTC 6 2.45097e+02 0.01828840
## X24h_volume_usd market_cap_usd available_supply total_supply max_supply
## 1 14254300000 226178291103 16777187 16777187 2.1e+07
## 2 2126830000 89074077921 38739144847 99993093880 1.0e+11
## 3 4720680000 85240084528 96718654 96718654 NA
## 4 1086780000 41346668220 16888875 16888875 2.1e+07
## 5 158158000 18279388468 25927070538 31112483745 4.5e+10
## 6 846307000 13376814153 54577633 54577633 8.4e+07
## percent_change_1h percent_change_24h percent_change_7d last_updated
## 1 0.88 -3.32 -10.65 1514877260
## 2 1.85 2.03 104.76 1514877241
## 3 0.88 14.21 13.91 1514877249
## 4 0.13 -2.59 -18.72 1514877253
## 5 0.69 -0.43 68.51 1514877255
## 6 1.75 5.04 -12.85 1514877241subcrypto<-crypto.df[6:15]
subcrypto1<-subcrypto[c(-3,-4,-6)]
subcryp <- crypto.df[crypto.df$available_supply !=0 ,]
subcryp1 <- subcryp[subcryp$X24h_volume_usd !=0 ,]
subcryp1<- subcryp1[order(subcryp1$rank),]
f.Result:
This paper was motivated by the need for research that could improve our understanding of Cryptocurrency influences the price increase strategies in the world . The unique contribution of this paper is that we investigated the price premium charged. We observed currencies charging price based on these parameters.
#Conclusion:
Our observation gave an overall view of our prediction and dependecies by which we can predict why currencies are differed every time . this result gave us a basic overview of what is crypto currency why it differs . which parameters are the main reason for this change.
Reference:
https://en.wikipedia.org/wiki/Cryptocurrency
https://blockgeeks.com/guides/what-is-cryptocurrency
https://stackoverflow.com/questions/tagged/r
https://www.r-project.org/mail.html
http://www.independent.co.uk/life-style/gadgets-and-tech/news/bitcoin-price-live-updates-latest-value-exchange-rate-digital-cryptocurrency-futures-investment-a8184781.html
Summary Statistics from the cryptocurrency data
->Descriptive statistics (min, max, median etc) of each variable
library(psych)
describe(crypto.df)## Warning in describe(crypto.df): NAs introduced by coercion
## Warning in describe(crypto.df): NAs introduced by coercion
## Warning in describe(crypto.df): 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 max; returning
## -Inf## vars n mean sd median
## X 1 1381 6.910000e+02 3.988000e+02 6.910000e+02
## id* 2 1381 NaN NA NA
## name* 3 1381 1.337000e+03 NA 1.337000e+03
## symbol* 4 1381 Inf NaN 8.080000e+02
## rank 5 1381 6.910000e+02 3.988000e+02 6.910000e+02
## price_usd 6 1379 1.026730e+03 2.596996e+04 1.200000e-01
## price_btc 7 1379 8.000000e-02 1.940000e+00 0.000000e+00
## X24h_volume_usd 8 1329 2.833863e+07 4.327306e+08 2.159430e+04
## market_cap_usd 9 1079 5.812979e+08 7.991407e+09 4.326552e+06
## available_supply 10 1079 8.663087e+09 1.212343e+11 2.302034e+07
## total_supply 11 1262 7.481779e+11 2.596479e+13 4.501933e+07
## max_supply 12 246 4.102795e+12 6.375730e+13 1.010000e+08
## percent_change_1h 13 1333 1.440000e+00 1.107000e+01 1.210000e+00
## percent_change_24h 14 1338 1.053000e+01 4.885000e+01 2.000000e+00
## percent_change_7d 15 1325 4.814000e+01 1.478300e+02 1.324000e+01
## last_updated 16 1379 1.514872e+09 6.330238e+04 1.514877e+09
## trimmed mad min max
## X 6.910000e+02 511.50 1.00 1.381000e+03
## id* NaN NA Inf -Inf
## name* 1.337000e+03 0.00 1337.00 1.337000e+03
## symbol* Inf 753.16 42.00 Inf
## rank 6.910000e+02 511.50 1.00 1.381000e+03
## price_usd 6.800000e-01 0.18 0.00 8.749520e+05
## price_btc 0.000000e+00 0.00 0.00 6.529000e+01
## X24h_volume_usd 5.563710e+05 31981.80 0.32 1.425430e+10
## market_cap_usd 2.209816e+07 6334448.53 13.00 2.261783e+11
## available_supply 9.098716e+07 32492283.54 0.00 3.386511e+12
## total_supply 2.020766e+08 64370211.73 1.00 9.223429e+14
## max_supply 6.436173e+08 142329600.00 300.00 1.000000e+15
## percent_change_1h 1.110000e+00 1.57 -77.05 2.367500e+02
## percent_change_24h 4.630000e+00 12.59 -81.09 9.377000e+02
## percent_change_7d 2.410000e+01 36.00 -85.50 3.252430e+03
## last_updated 1.514877e+09 7.41 1513173873.00 1.514877e+09
## range skew kurtosis se
## X 1.380000e+03 0.00 -1.20 1.073000e+01
## id* -Inf NA NA NA
## name* 0.000000e+00 NA NA NA
## symbol* Inf NaN NaN NaN
## rank 1.380000e+03 0.00 -1.20 1.073000e+01
## price_usd 8.749520e+05 30.31 968.17 6.993400e+02
## price_btc 6.529000e+01 30.31 968.17 5.000000e-02
## X24h_volume_usd 1.425430e+10 28.22 889.71 1.187012e+07
## market_cap_usd 2.261783e+11 23.35 611.87 2.432834e+08
## available_supply 3.386511e+12 23.18 597.20 3.690750e+09
## total_supply 9.223429e+14 35.43 1254.65 7.308952e+11
## max_supply 1.000000e+15 15.49 238.99 4.065017e+12
## percent_change_1h 3.138000e+02 10.41 205.85 3.000000e-01
## percent_change_24h 1.018790e+03 9.70 141.08 1.340000e+00
## percent_change_7d 3.337930e+03 10.43 182.67 4.060000e+00
## last_updated 1.703391e+06 -20.93 496.56 1.704660e+03Boxplot of the variables .
#currency in usd
boxplot(log(crypto.df$price_usd) , col ="red" , main= "Currencies comapison using USD as a parameter ")
boxplot(log(crypto.df$price_btc),col = "blue" , main= "Currencies comapison using Bit coins as a parameter ")
Histograms
hist(crypto.df$percent_change_1h ,main = "percentage change in 1hr" ,col = c(12,38))
hist(crypto.df$percent_change_24h , main = "percentage change in 24hr" ,col = c(15,8))
hist(crypto.df$percent_change_7d, main = "percentage change in 7days", col=c(19,22))
After seeing this histogram a huge difference occurred between 1hr ,24hr and 7days
Suitable plot
plot(log(crypto.df$market_cap_usd), main = "market capacity")
Market Capacity
library(treemap)
market_today <- read.csv('cryptocurrencies_prices.csv',header = T, stringsAsFactors = F)
df1 <- na.omit(market_today[,c('id','market_cap_usd')])
df1$market_cap_usd <- as.numeric(df1$market_cap_usd)
df1$formatted_market_cap <- paste0(df1$id,'\n','$',format(df1$market_cap_usd,big.mark = ',',scientific = F, trim = T))
treemap(df1, index = 'formatted_market_cap', vSize = 'market_cap_usd', title = 'Cryptocurrency Market Cap', fontsize.labels=c(12, 8), palette='RdYlGn')
Correlation matrix:
library(Hmisc)## Loading required package: lattice## Loading required package: survival## Loading required package: Formula## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alpha##
## Attaching package: 'Hmisc'## The following object is masked from 'package:psych':
##
## describe## The following objects are masked from 'package:base':
##
## format.pval, unitsrcorr(as.matrix(subcrypto1))## price_usd price_btc available_supply max_supply
## price_usd 1.00 1.00 0.00 -0.01
## price_btc 1.00 1.00 0.00 -0.01
## available_supply 0.00 0.00 1.00 0.00
## max_supply -0.01 -0.01 0.00 1.00
## percent_change_1h 0.00 0.00 -0.03 -0.04
## percent_change_24h 0.00 0.00 0.05 -0.02
## percent_change_7d -0.01 -0.01 0.19 -0.01
## percent_change_1h percent_change_24h percent_change_7d
## price_usd 0.00 0.00 -0.01
## price_btc 0.00 0.00 -0.01
## available_supply -0.03 0.05 0.19
## max_supply -0.04 -0.02 -0.01
## percent_change_1h 1.00 0.27 0.10
## percent_change_24h 0.27 1.00 0.29
## percent_change_7d 0.10 0.29 1.00
##
## n
## price_usd price_btc available_supply max_supply
## price_usd 1379 1379 1079 246
## price_btc 1379 1379 1079 246
## available_supply 1079 1079 1079 218
## max_supply 246 246 218 246
## percent_change_1h 1333 1333 1058 245
## percent_change_24h 1338 1338 1056 245
## percent_change_7d 1325 1325 1058 239
## percent_change_1h percent_change_24h percent_change_7d
## price_usd 1333 1338 1325
## price_btc 1333 1338 1325
## available_supply 1058 1056 1058
## max_supply 245 245 239
## percent_change_1h 1333 1304 1291
## percent_change_24h 1304 1338 1302
## percent_change_7d 1291 1302 1325
##
## P
## price_usd price_btc available_supply max_supply
## price_usd 0.0000 0.9176 0.9066
## price_btc 0.0000 0.9176 0.9065
## available_supply 0.9176 0.9176 0.9973
## max_supply 0.9066 0.9065 0.9973
## percent_change_1h 0.9778 0.9778 0.3539 0.4912
## percent_change_24h 0.9080 0.9079 0.1258 0.7444
## percent_change_7d 0.6531 0.6532 0.0000 0.8555
## percent_change_1h percent_change_24h percent_change_7d
## price_usd 0.9778 0.9080 0.6531
## price_btc 0.9778 0.9079 0.6532
## available_supply 0.3539 0.1258 0.0000
## max_supply 0.4912 0.7444 0.8555
## percent_change_1h 0.0000 0.0004
## percent_change_24h 0.0000 0.0000
## percent_change_7d 0.0004 0.0000Correlation matrix using corrgram
library(coefplot)
library(corrgram)
corrgram(subcrypto1,lower.panel=panel.pts, upper.panel=panel.pie,
diag.panel=panel.minmax, text.panel=panel.txt)
Scatterplot Matrix:
library(car)##
## Attaching package: 'car'## The following object is masked from 'package:psych':
##
## logitscatterplotMatrix(~subcrypto1$percent_change_1h+subcrypto1$percent_change_24h+subcrypto1$percent_change_7d , col = c(5,15,8,39,35) )
Model
mod1<- percent_change_1h~percent_change_24h+percent_change_7d
fit1<-lm(mod1, data = crypto.df)
summary(fit1)##
## Call:
## lm(formula = mod1, data = crypto.df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -72.481 -1.344 0.435 1.481 200.005
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.549830 0.294287 1.868 0.0619 .
## percent_change_24h 0.060012 0.005890 10.188 <2e-16 ***
## percent_change_7d 0.003431 0.002361 1.453 0.1464
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.724 on 1270 degrees of freedom
## (108 observations deleted due to missingness)
## Multiple R-squared: 0.0892, Adjusted R-squared: 0.08776
## F-statistic: 62.19 on 2 and 1270 DF, p-value: < 2.2e-16We can see that the p value is <.05 so we can say that our hypothesis is accepted and we can predict the value using the markets condition.
attach(crypto.df)
t.test(percent_change_1h,percent_change_24h)##
## Welch Two Sample t-test
##
## data: percent_change_1h and percent_change_24h
## t = -6.6379, df = 1474.4, p-value = 4.458e-11
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -11.776400 -6.403925
## sample estimates:
## mean of x mean of y
## 1.440503 10.530665t.test(percent_change_1h,percent_change_7d)##
## Welch Two Sample t-test
##
## data: percent_change_1h and percent_change_7d
## t = -11.466, df = 1338.8, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -54.68409 -38.70564
## sample estimates:
## mean of x mean of y
## 1.440503 48.135366t.test(percent_change_24h,percent_change_7d)##
## Welch Two Sample t-test
##
## data: percent_change_24h and percent_change_7d
## t = -8.7961, df = 1607.2, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -45.99017 -29.21923
## sample estimates:
## mean of x mean of y
## 10.53067 48.13537Applying t-test we can see the above result so we can accept the data as p value <.05 so we can accept the null hypothesis .