Datathon Telenor Solution – The Telenor case

Posted Leave a commentPosted in Prediction systems

  Answering questions: Top 10 ravens by number of non-zero delays, aggregated over family, family members and network FIRST_GET_RESPONSE_SUCCESS_D PAGE_BROWSING_DELAY TCP_SETUP_TOTAL_DELAY PAGE_CONTENT_DOWNLOAD_TOTAL_D FIRST_DNS_RESPONSE_SUCCESS_D DNS_RESPONSE_SUCCESS_DELAY FIRST_TCP_RESPONSE_SUCCESS_D PAGE_SR_DELAYS SYN_SYN_DELAY TCP_CONNECT_DELAY PAGE_BROWSING_DELAYS Loving raven Maxwell Brass raven Birdy Brass raven Birdy Brass raven Birdy Brass raven Birdy Brass raven Birdy Brass raven Birdy Brass raven Birdy Brass raven […]

Cryptocurrency Prediction by Kautilya

Posted 6 CommentsPosted in Datathons Solutions, Learn, Team solutions

Given the cryptocurrencies’ data, we aim to forecast the future cryptocurrencies’ prices so as to execute profitable trades. We show that the cryptocurrencies’ prices also exhibit desirable properties such as stationarity and mixing. Some classical time series prediction models that exploit this behavior, such as “Arima” models produce poor predictions and also lack good probabilistic interpretations. We have introduced a theoretical framework in the 1st place and for predicting and trading prices of the cryptocurrencies for future and based on that we have designed our model which is based on “Neural Network” model which can give better prediction values as compared to the other models.