Sold by: i4cast LLCÂ
Deployed on AWS
Free Trial
Dynamic Factor Based Volatility Index Forecast (DFbVIF) model for multi-step multivariate forecasts of (options-implied) volatility indexes
Overview
DFbVIF (dynamic factor based volatility index forecast) model/algorithm is to make multi-step forecasts of multiple volatility indexes. Widely watched volatility indexes include VIX (on S&P 500) and VXN (on Nasdaq 100) published by CBOE. Holistic data-driven models analyzing and forecasting volatility indexes could serve as important tools. Many volatility indexes, price time-series underlying these volatility indexes, and numerous information-enhancing time-series dynamically correlated with the underlying time-series, can be modeled, analyzed, and forecasted together by dynamic factor models (DFMs). DFbVIF applies DFM volatility analysis (DFVCM) on the underlying and information-enhancing time-series. Then, the volatility forecasts of the underlying time-series are transformed into multi-step forecasts of the volatility indexes. Currently, DFbVIF offers two transforms: UVF (underlying volatility forecasts as predictors) and QAR (quadratic autoregressive forecasts).
Highlights
- Forecasting multiple volatility indexes by powerful DFM analysis. In the era of big data machine learning, well-established DFM (dynamic factor model) is further developed into a new engine for volatility analysis. Advantages of DFM-based volatility analysis over others include: (1) noise-resistant analysis on large number of time-series due to dimension reduction, (2) dynamic modeling by estimating vector autocovariances of many different time-lags, (3) variance forecast by representation of quadratic autoregression (QAR), and (4) volatility attribution to dynamic sources.
- Adding information-enhancing data set, or informational dynamic predictors, to increase predictive poser. Due to big data capacity of DFM estimated by DPCA (dynamic PCA), input data set, of (1) multiple volatility indexes and (2) price/index/value time-series underlying the volatility indexes, can be sufficiently expanded by (3) many other time-series dynamically correlated with the underlying time-series. This data addition enhances the information set for the predictive modeling.
- Dynamic volatility attributions. Volatility attributions can serve as predictors for volatility forecasts with other models. For example, “mean reversion” of volatility is a forecaster with static contributor(s) as predictor(s). A dynamic volatility attribution adds levels of vector autocovariances and individual serial-correlations as dynamic predictors. Higher autocorrelations indicate panic or stampede. Therefore, a dynamic volatility attribution gives more predictive information than a static one. Both DFbVIF and underlying DFVCM algorithms offer dynamic volatility attributions.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 120 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $0.10 |
ml.m5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.10 |
ml.m5.xlarge Training Recommended | Algorithm training on the ml.m5.xlarge instance type | $0.10 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $0.10 |
ml.g4dn.4xlarge Inference (Batch) | Model inference on the ml.g4dn.4xlarge instance type, batch mode | $0.10 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $0.10 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $0.10 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $0.10 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $0.10 |
ml.g4dn.2xlarge Inference (Batch) | Model inference on the ml.g4dn.2xlarge instance type, batch mode | $0.10 |
Vendor refund policy
We offer full refund for academic works. Other refunds are offered according to common practices.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
DFbVIF model/algorithm makes multi-step forecasts of multiple volatility indexes, such as VIX (on S&P 500) and VXN (on Nasdaq 100) published by CBOE.
Many volatility indexes, price time-series underlying these volatility indexes, and numerous information-enhancing time-series dynamically correlated with the underlying time-series, can be modeled, analyzed, and forecasted together by dynamic factor models (DFMs).
DFbVIF applies DFM volatility analysis and then transforms volatility forecasts of the underlying time-series into multi-step forecasts of volatility indexes.
Additional details
Inputs
- Summary
DFbVIF takes THREE sets of input data: (1) volatility index time-series, (2) price/index time-series underlying the volatility indexes, and (3) information-enhancing time-series dynamically correlated with the underlying time-series, all together contained in a CSV data table.
Each row of the data table is an individual time-series. Each column is a sample at a specific moment in time. The first data column is for the earliest time and the last column for the most recent time.
- Limitations for input type
- Equal spaced in time, and no missing values.
- Input MIME type
- text/csv
https://github.com/i4cast/aws/blob/main/dfm-based_volatility_index_forecast_model/input/Weekly_MTS_6Yr.csv
https://github.com/i4cast/aws/blob/main/dfm-based_volatility_index_forecast_model/input/Weekly_MTS_6Yr.csv
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
Values of time stamp | DFbVIF takes THREE sets of input data: (1) volatility index time-series, (2) price/index time-series underlying the volatility indexes, and (3) information-enhancing time-series dynamically correlated with the underlying time-series, all together contained in a CSV data table.
Each row of the data table is an individual time-series. Each column is a sample at a specific moment in time. The first data column is for the earliest time and the last column for the most recent time. | Type: FreeText
Limitations: Equal spaced in time, and no missing values. | Yes |
Support
Vendor support
For questions or call-back number, please send email to i4cast LLC at prod.i4cast@gmail.com .
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Long-Memory Dynamic Factor Model (LMDFM) to analyze and forecast large number of time-series influenced by evolutions of unobserved factors.
Dynamic Factor Variance-Covariance Model (DFVCM) makes multi-step forecasts of large variance-covariance matrix with dynamic factor model.
Continuously Trained Vector Autoregressive Forecast (CTVARF) for multiple time-series influenced by common factors and hidden components.
Long-Memory Vector Autoregression (LMVAR) to analyze and forecast multiple time-series influenced by common factors and hidden components.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.