CLIAMS:We Claim:

1. A method of predicting in real time timely delivery of telecom services to a customer, the method comprising:
receiving, by a processor of a prediction device, order data collected for a predetermined time period from a telecom service provider repository, the order data comprising data corresponding to one or more first variables associated with a plurality of telecom service orders;
processing, by the processor, the received order data to generate a processed order data comprising one or more second variables and one or more missing data corresponding to the first variables derived from the received order data;
generating, by the processor, a plurality of models based on one or more first and second variables identified from the processed order data;
selecting, by the processor, a model having a minimum model generation error rate among the plurality of models thus generated; and
predicting, by the processor, the timely delivery of the telecom services based on the selected model and real time order data.
2. The method as claimed in claim 1, wherein processing the received order data comprising the steps of:
identifying the one or more second variables required for predicting the real time delivery;
deriving data corresponding to the one or more second variables based on the data corresponding to the first variables; and
determining the one or more missing data of the first variables and adding the determined missing data corresponding to the first variables in the order data.
3. The method as claimed in claim 1, wherein upon processing the received order data, the method comprising the step of partitioning the processed order data into at least a training data set, a validation data set and a testing data set, each data set comprising at least a subset of data corresponding to the first and second variables of the processed order data.
4. The method as claimed in claims 1 and 3, wherein generating the plurality of models comprising the steps of:
identifying one or more third, fourth, fifth and sixth variables respectively from the training data set;
generating at least a decision tree model, a prediction tree model, a regression model and a neural network model respectively based on the identified third, fourth, fifth and sixth variables of the training data set; and
determining the validity of the generated plurality of models based on the validation data set.

5. The method as claimed in claim 4, wherein generating the neural network model comprising the steps of:
identifying the one or more sixth variables from the training data set that are inconsistent with the remaining of the first and second variables in the training data set;
eliminating the one or more identified sixth variables from the training data set to generate a consistent training data set comprising one or more seventh variables; and
generating the neural network model based on the one or more seventh variables of the consistent training set.

6. The method as claimed in claims 1 and 3, wherein the step of selecting the model among the plurality of models comprising:
determining a first model generation error rate associated with generation of the plurality of models based on the training data set;
determining a second model generation error rate associated with generation of the plurality of models based on the validation data set;
comparing the first model generation error rate and the second model generation error rate thus determined;
determining a minimum model generation error rate based on the comparison; and
selecting the model having the minimum model generation error rate thus determined.

7. A prediction device for predicting in real time timely delivery of telecom services to a customer, comprising:
a processor;
a telecom service provider repository coupled with the processor and configured to store order data associated with a plurality of telecom service orders; and
a memory disposed in communication with the processor and storing processor-executable instructions, the instructions comprising instructions to:
receive the order data collected for a predetermined time period from the telecom service provider repository;
process the received order data to generate a processed order data comprising one or more second variables and one or more missing data corresponding to the first variables derived from the received order data;
generate a plurality of models based on one or more first and second variables identified from the processed order data;
select a model having a minimum model generation error rate among the plurality of models thus generated; and
predict the timely delivery of the telecom services based on the selected model and real time order data.

8. The device as claimed in claim 7, wherein the processor is configured to process the received order data by performing the steps of:
identifying the one or more second variables required for predicting the real time delivery;
deriving data corresponding to the one or more second variables based on the data corresponding to the first variables; and
determining the one or more missing data of the first variables and adding the determined missing data corresponding to the first variables in the received order data.

9. The device as claimed in claim 7, wherein upon processing the received order data, the processor is configured to partition the processed order data into at least a training data set, a validation data set and a testing data set, each data set comprising at least a subset of data corresponding to the first and second variables of the processed order data.

10. The device as claimed in claims 7 and 9, wherein the processor is configured to generate the plurality of models by performing the steps of:
identifying one or more third, fourth, fifth and sixth variables respectively from the training data set;
generating at least a decision tree model, a prediction tree model, a regression model and a neural network model respectively based on the identified third, fourth, fifth and sixth variables of the training data set; and
determining the validity of the generated plurality of models based on the validation data set.
11. The device as claimed in claim 10, wherein the processor is configured to generate the neural network model by the steps of:
identifying the one or more sixth variables from the training data set that are inconsistent with the remaining of the third variables in the training data set;
eliminating the one or more identified sixth variables from the training data set to generate a consistent training data set comprising one or more seventh variables; and
generating the neural network model based on the one or more seventh variables of the consistent training set.
12. The device as claimed in claims 7 and 9, wherein the processor is configured to select the model among the plurality of models by performing the steps of:
determining a first model generation error rate associated with generation of the plurality of models based on the training data set;
determining a second model generation error rate associated with generation of the plurality of models based on the validation data set;
comparing the first model generation error rate and the second model generation error rate thus determined;
determining a minimum model generation error rate based on the comparison; and
selecting the model having the minimum model generation error rate thus determined.
13. A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor cause a system to perform acts of:
receiving order data related to a predetermined time period comprising one or more first variables associated with a plurality of telecom service orders;
processing the received order data to generate a processed order data comprising one or more second variables and one or more missing data corresponding to the first variables derived from the received order data;
generating a plurality of models based on one or more first and second variables identified from the processed order data;
selecting a model having a minimum model generation error rate among the plurality of models thus generated; and

predicting the timely delivery of the telecom services based on the selected model and real time order data.

Dated this 30th day of March, 2015

M.S. Devi
Of K&S Partners
Agent for the Applicant
,TagSPECI:FIELD OF THE DISCLOSURE
The present subject matter is related, in general to predictive modeling, and more particularly, but not exclusively to method and device for predicting timely delivery of telecom service orders in real time.