Data conversion and distribution systems
Systems and methods for improved data conversion and distribution are provided. A data subscription unit is configured to receive data and information from a plurality of data source devices. The data subscription unit is in communication with a virtual machine that includes backtesting utility configured to generate backtesting data using one or more statistical models and one or more non-statistical models. The backtesting utility may translate the backtesting results into one or more interactive visuals, and generate a graphical user interface (GUI) for displaying the backtesting results and the one or more interactive visuals on a user device. The backtesting utility may update one or more of the displayed backtesting results and the one or more interactive visuals without re-running the modeling steps.
1. A method of dynamically updating model results, the method comprising:
in a system comprising one or more processors configured to communicate with at least one user device, and a non-transitory memory storing machine-readable instructions executable by the one or more processors:
receiving data from one or more data sources, the data including real-time data;
generating an interactive graphical user interface (GUI) on the at least one user device, the interactive GUI comprising one or more windows, the one or more windows including a user input portion and a results portion, the user input portion including one or more user-selectable parameters for generating customizable backtesting analytics, the results portion configured to display the customizable backtesting analytics;
applying, responsive to user input via the user input portion of the interactive GUI, including at least one selected parameter among the one or more user-selectable parameters, the at least one selected parameter to the received data to generate backtesting data specific to the user input;
modeling the generated backtesting data by initiating one or more models to produce model results, wherein the one or more models include at least one of:
one or more non-statistical models that, when run, generate one or more security level metrics, aggregate statistics and time-dependent aggregate statistics, and
one or more statistical models that, when run, utilize statistically significant features from among the backtesting data to generate, as part of the model results, one or more relationship coefficients based on the statistically significant features;
generating graphic backtesting analytic indicators representative of the model results and specific to the user input in the results portion of the interactive GUI; and
dynamically regenerating, in real-time, the results portion of the interactive GUI to display updates to the graphic backtesting analytic indicators based on one or more changes to the received data without generating any further windows in the interactive GUI,
wherein the updates to the graphic backtesting analytic indicators are triggered by at least one of additional user input entered into said interactive GUI and changes to any of the received data, the method further comprising automatically reinitiating the one or more models to account for said additional user input and said changes to the received data.
2. The method of claim 1 , wherein the real-time data includes real-time market data, the method further comprising:
dynamically regenerating the graphic backtesting analytic indicators based on changes to the real-time market data.
3. The method of claim 1 , wherein the data includes a combination of data quote counts, transaction counts, and transaction volume values corresponding to a time window.
4. The method of claim 1 , wherein the one or more user-selectable parameters comprise one or more of one or more data filtering parameters and one or more backtesting analytics parameters.
5. The method of claim 1 , wherein the one or more user-selectable parameters comprise at least one of first-layer conditions, second-layer conditions, and third-layer conditions.
6. The method of claim 5 , wherein the third-layer conditions include the second-layer conditions and the first-layer conditions, and the second-layer conditions include the first-layer conditions.
7. The method of claim 5 , wherein the first-layer conditions comprise one or more of a financial security parameter, a portfolio parameter, an asset class parameter, a date range, a specific date, a specific time of day, and one or more target backtesting analytics.
8. The method of claim 5 , wherein the second-layer conditions comprise one or more of a price-type criteria, a trade size criteria, an optimal institutional trade size calculation and selection parameter, a lookback time period criteria, conditional filtering criteria and analytics filtering criteria.
9. The method of claim 5 , wherein the third-layer conditions comprise one or more of real time regeneration of initial backtesting analytics, discrete, range, or multi-selection results generation, and security-level attributes criteria.
10. The method of claim 1 , further comprising sorting a portion of the backtesting data according to one or more sorting criteria.
11. The method of claim 1 , wherein the one or more models comprise a combination of the one or more statistical models and the one or more non-statistical models.
12. The method of claim 1 , wherein the one or more models comprises one or more machine learning models.
13. The method of claim 1 , further comprising:
adjusting, via the interactive GUI, responsive to further user input, how the graphic backtesting analytic indicators are displayed.
14. The method of claim 13 , wherein said adjusting comprises at least one of: moving a position of at least one of the graphic backtesting analytic indicators within the results portion, zooming in on one or more of the graphic backtesting analytic indicators, and analytic indicator extraction.
15. The method of claim 1 , further comprising:
using machine learning to automatically generate an interpretation of the model results and to display the interpretation via the interactive GUI.