Claims:WE CLAIM:

1. A method of predicting future events by analyzing real-time Internet of things (IoT) data, the method comprising:
acquiring, by an analytics and prediction device, the real-time IoT data corresponding to one or more IoT devices;
building, by the analytics and prediction device, a predictive model based on the real-time IoT data, wherein the predictive model comprises a machine learning algorithm that generates an output parameter representing a future event based on a set of input parameters derived from the real-time IoT data, and wherein building the predictive model comprises training the predictive model for one or more explanatory input parameters and an expected output parameter;
predicting, by the analytics and prediction device, the future event based on the real-time IoT data using the predictive model;
determining, by the analytics and prediction device, a deviation between the future event and an actual event; and
tuning, by the analytics and prediction device, the predictive model based on the deviation.

2. The method of claim 1, further comprising:
receiving real-time streaming IoT data from the one or more IoT devices through a data streaming platform; and
storing the real-time streaming IoT data in a big data warehouse for a pre-defined time period.

3. The method of claim 2, wherein acquiring the real-time IoT data comprises:
extracting the real-time streaming IoT data from the big data warehouse;
transforming the real-time streaming IoT data into a structured data format; and
organizing the transformed real-time streaming IoT data in a hive database.

4. The method of claim 1, wherein the predictive model comprises at least one of a liner regression model, a logistic regression model, a random forest model, or an extreme gradient boosting (XgBoost) model.

5. The method of claim 1, wherein tuning the predictive model further comprises:
evaluating one or more characteristic indices of the predictive model within a pre-defined time period; and
tuning the predictive model based on the evaluation.

6. The method of claim 5, wherein the one or more characteristic indices comprises at least one of a population stability index (PSI), a coefficient stability index (CSI), or a Kolmogorov-Smirnov (KS) value.

7. A system for predicting future events by analyzing real-time Internet of things (IoT) data, the system comprising:
an analytics and prediction device comprising at least one processor and a computer-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
acquiring the real-time IoT data corresponding to one or more IoT devices;
building a predictive model based on the real-time IoT data, wherein the predictive model comprises a machine learning algorithm that generates an output parameter representing a future event based on a set of input parameters derived from the real-time IoT data, and wherein building the predictive model comprises training the predictive model for one or more explanatory input parameters and an expected output parameter;
predicting the future event based on the real-time IoT data using the predictive model;
determining a deviation between the future event and an actual event; and
tuning the predictive model based on the deviation.

8. The system of claim 7, wherein the operations further comprise:
receiving real-time streaming IoT data from the one or more IoT devices through a data streaming platform; and
storing the real-time streaming IoT data in a big data warehouse for a pre-defined time period.

9. The system of claim 8, wherein acquiring the real-time IoT data comprises:
extracting the real-time streaming IoT data from the big data warehouse;
transforming the real-time streaming IoT data into a structured data format; and
organizing the transformed real-time streaming IoT data in a hive database.

10. The system of claim 7, wherein the predictive model comprises at least one of a liner regression model, a logistic regression model, a random forest model, or an extreme gradient boosting (XgBoost) model.

11. The system of claim 7, wherein tuning the predictive model further comprises:
evaluating one or more characteristic indices of the predictive model within a pre-defined time period; and
tuning the predictive model based on the evaluation.

12. The system of claim 11, wherein the one or more characteristic indices comprises at least one of a population stability index (PSI), a coefficient stability index (CSI), or a Kolmogorov-Smirnov (KS) value.

Dated this 19th day of September 2018

Swetha SN
Of K&S Partners
Agent for the Applicant
IN/PA-2123
, Description:TECHNICAL FIELD
This disclosure relates generally to Internet of Things (IoT), and more particularly to method and system for analyzing IoT data in real-time and providing predictions.