With 1.7 million freelancers, we'll match you with the perfect talent.
The client has made the following changes to the job.
Client prefers freelancers from:
You are still able to submit a proposal for this job.
The client prefers freelancers from
a different location.
The scope of the project is to design an alogrithm for forecasting high-volatility time series.
- input: 1..n time series objects (n>=1)
- target: 1..m time series objects (m>=1)
- forecast: 1..k samples, on m time series
Each time series object (input, targets) will have the same number of samples, each one with Open,Close,High,Low values. Number of input/target can be high if needed.
- system must be based on neural networks
- all network's features must be configred as "parameters" into algorithm code
- input data must be read from text files
- must include pre-post processing data normalization module
- system output must be stored into variables + saved into txt files
- system spurce code must be developed in Matlab but must be ready to be migrated to C/C++ or to other languages
- bidder can consider the use of NN toolbox
- must include "tester" module (after training phase; data for testing could be different from those...
Sign in or Register to see more