“IMAGINE, INNOVATE and INSPIRE“
KAUTILYA Team Mentors:
- Subhabaha Pal(@drsubhabahapal)
- Prakash Kumar (@prakash), MAHE, India
- Sujit Mohapatra(@sujit), MAHE, India
- Vivek Arya (@svarya), MAHE, India
- Amit Kumar Mohapatra (@amit98), MAHE, India
- Vijay (@vijays), MAHE, India
- R-Studio: Neural Network Time Series Forecasting
- MS Excel
- Who: Data Science Society (Academic Datathon) Organizers
- What (1): Make a prediction model of the major cryptocurrencies’ prices
- How: Intra-group brainstorming based on various concepts of time series analysis and machine learning.
- Explore dataset’s structure
- Discover potential variable dependencies across datasets
- Identify the missing data points across the dataset
- Identify the subsets of data that modeling would be based on
The cryptocurrencies data had many NA values and deleted (absent) rows for particular time points, which are common in any financial time series. So we created time points with NAs in rows using Microsoft Excel. The NAs were then imputed using a function from” imputeTS” library of R. The total dataset was then subset to create the desired model.
- For the target forecast, two approaches opted: the forecast to be made on per 5 minutes data of each day as the cryptocurrencies market works on 24*7. The two approaches on which we have worked on are i. “auto.arima”, ii. “nnetar”.We ensured that there are no variables with a large percent of missing/outlier values.
- The prices of cryptocurrencies for 25th Jan 2018 with 288-time points were predicted.
The subset of the dataset had price values of currencies for the month of January. The starting time point was taken as 18th Jan 2018 00:00 and end time point was taken to be 24th Jan 2018 23:55 for training the model and which predicts the 25th Jan 00:00. Keeping these things in mind the model predicts the currencies’ prices one by one. The model has been formed as per the following procedure and so on.
- The main problem was with the dataset which is not continuous due to which we have to hit and trial some methods for missing data treatment and imputation.
- Due to the missing values for which the data points have been imputed, the actual values may vary as in some cases the data points are missing for 2 or more time points.
Select the below link to download the codes
In general, the provided code would not give predictions for the required dates:
30.01.2018, 06.02.2018, 20.02.2018, 09.03.2018, 18.03.2018
That said, the code is well documented and seems to be fairly easy to be extended to include the required time period.
It will test for the goodness of the predictions.
A bit more explanatory text what the nnetar function does and how it was used would be beneficial.
The input data used has not been provided, so I am unable to run the code as is.
Yep, It wont give the predictions for the dates because it will give 5 day predictions of all cryptocurrencies starting from 25th Jan 2018. But we can predict for the given dates by varying the value of k. That’s how we predicted 30th Jan.
1. You may want to include some evaluation metrics for your models both on train & test sets.
2. On the data prep part – it is not the best solution to just remove rows where you see missing values because it is time-series data and could seriously bias your next steps.
3. Assumption you have made about the “large number of missing values” is probably poor. Do you have any data/metric you used to prove it?
4. You may want to include more detailed explanation why the data is not continuous (here is a link on discrete and continuous data https://www.mathsisfun.com/data/data-discrete-continuous.html)
5. How you would rank your model? What are the metrics you used?
Sorry but I feel there is some misinterpretation. We have not deleted any rows rather than we have imputed using “na.kalman” of library “imputeTS” using “auto.arima” model. There were lot of missing rows and many time interval were missing.
6. Would you bet your own money on your predictions? If so how much?
this is actually sensible approach, but what troubles me is overfitting.
My hope in crypto is renewed after a recovery expert I hired when a sim-swap hack was carried out on my device leaving my crypto account vulnerable. My wallet was accessed and coins moved outside to an external wallet. JimfundsrecoveryAt Consultant C0m simply pursued my case with a local police report I made/ some required info and was able to recover 95% for me in a 2 weeks long recovery process.
Thanks to Mrs Jane who helped me recover all my lost funds in forex and crypto trading including my profits, i was a big fool giving my hard earned money to greedy and scammed brokers, but am so happy i met Jane silva a honest woman who helped me recover all my lost funds, and she also gave me the right signal and platform to trade with, now am able to make $5000 weekly, and am very happy, that is why i cant stop testifying about her, if you are out there still experiencing failure trading in binary option, crypto and forex trading or you want to recover your lost funds trading in binary/ forex trade i will advice you to reach out to
her via email on janesilva0727 gmail com
About five years ago, I heard a prediction that Bitcoin would be worth a hundred thousand dollars, but so far these predictions have not come true. Personally, I have always preferred to invest in Ethereum. I recently managed to buy crypto with credit card on Switchere.com and it was quite unusual. I have never seen exchangers selling crypto for credit money. In any case, I will take note of this site.