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:
receiving, by at least one server, data from one or more data sources, the at least one server comprising one or more processors and a non-transitory memory;
generating, by the at least one server, an interactive graphical user interface (GUI) on at least one user device, the interactive GUI comprising one or more windows including a configuration interface and a results dashboard, the configuration interface including one or more user-selectable parameters for generating customizable backtesting analytics, the results dashboard configured to display the customizable backtesting analytics;
receiving, via the configuration interface of the interactive GUI, user input comprising one or more selections among the one or more user-selectable parameters to form a customized backtesting configuration;
applying, by the at least one server, the customized backtesting configuration to the received data to generate backtesting data specific to the user input;
modeling, by the at least one server, the generated backtesting data by initiating one or more models to produce model results, the one or more models including a combination of one or more non-statistical models and one or more statistical models, the model results comprising one or more of metrics and relationship information among the generated backtesting data;
generating, by the at least one server, in the results dashboard of the interactive GUI, graphic backtesting analytic indicators representative of the model results and specific to the customized backtesting configuration together with one or more filters for refining one or more backtesting parameters of the customized backtesting configuration; and
dynamically regenerating, by the at least one server, in real-time, the results dashboard of the interactive GUI to display updates to the graphic backtesting analytic indicators responsive to user selection of the one or more filters, without generating any further windows in the interactive GUI, the one or more models being automatically reinitiated to account for said user selection.
2. The method of claim 1 , wherein the 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 , further comprising:
automatically reinitiating the one or more models to account for changes in the received data.
5. The method of claim 1 , further comprising:
updating the graphic backtesting analytic indicators responsive to any changes in the received data.
6. 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.
7. The method of claim 1 , wherein the one or more user-selectable parameters 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 1 , wherein the one or more filters 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 1 , wherein the one or more filters 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 non-statistical models, when run, generate the metrics, the metrics comprising one or more of security level metrics, aggregate statistics and time-dependent aggregate statistics.
12. The method of claim 1 , wherein the one or more statistical models, when run, utilize statistically significant features from among the generated backtesting data to generate the relationship information, the relationship information comprising one or more relationship coefficients based on the statistically significant features.
13. The method of claim 1 , wherein the one or more models comprises one or more machine learning models.
14. 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.
15. The method of claim 14 , wherein the adjusting comprises at least one of: moving a position of at least one of the graphic backtesting analytic indicators within the results dashboard, zooming in on one or more of the graphic backtesting analytic indicators, and analytic indicator extraction.
16. 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.
17. The method of claim 1 , wherein the graphic backtesting analytic indicators comprise one or more interactive graphs.
18. The method of claim 1 , wherein the results dashboard further comprises a backtesting detail region configured to display information associated with the generated backtesting data.
19. The method of claim 18 , further comprising:
dynamically regenerating the results dashboard to display updates to the backtesting detail region responsive to the user selection of the one or more filters.
20. The method of claim 18 , wherein the backtesting detail region is configured to arrange the displayed information according to one or more categories.
21. The method of claim 20 , wherein the one or more filters correspond to the one or more categories.
22. The method of claim 20 , wherein the one or more categories comprise one or more of a security identifier, an asset class, a sector, a number of observations, a liquidity score, a security duration, security level metrics, aggregate statistics, and time-dependent aggregate statistics.