Abstract: An approach for spending allocation, executed by one or more processors to provide one or more monetary output values in response to a request for determining spending allocation in a digital marketing channel, is provided. The approach fits one or more models to train a business environment simulator. The approach generates a supervised learning policy. The approach evolves a supervised learning policy into a distribution estimator policy by adjusting network weights of the supervised learning policy. The approach generates an optimized policy by evolving the distribution estimator policy through interaction with the business environment simulator. The approach determines a profit uplift of the optimized policy by comparing the optimized policy and the supervised learning policy. Further, in response to the optimized policy outperforming the supervised learning policy, the approach deploys the optimized policy in a live environment.

Abstract: An approach for spending allocation, executed by one or more processors to provide one or more monetary output values in response to a request for determining spending allocation in a digital marketing channel, is provided. The approach fits one or more models to train a business environment simulator. The approach generates a supervised learning policy. The approach evolves a supervised learning policy into a distribution estimator policy by adjusting network weights of the supervised learning policy. The approach generates an optimized policy by evolving the distribution estimator policy through interaction with the business environment simulator. The approach determines a profit uplift of the optimized policy by comparing the optimized policy and the supervised learning policy. Further, in response to the optimized policy outperforming the supervised learning policy, the approach deploys the optimized policy in a live environment.

Abstract: Methods and systems for twisted pair telephone line diagnostics based on patterns of line data occurring over time. An observed data distribution is classified as periodic or based on modeled distributions previously determined to correspond to a known line activity, fault type, or fault location. A disruption or parameter value pattern is classified through statistical inference of operational and performance data collected from the line. Where the disruption and/or parameter value(s) correlate with a time the customer is at the customer premises, an inference is made that the line fault causing the disruption is more likely at the CPE than at the Central Office. Where the disruption distribution is classified as being a result of human activities initiated on the line, a fault condition associated with the activity is inferred. Where a disruption pattern is correlated with human initiated plain old telephone service (POTS), a micro-filter problem is inferred for the line.

Abstract: Methods and systems for twisted pair telephone line diagnostics based on patterns of line data occurring over time. An observed data distribution is classified as periodic or based on modeled distributions previously determined to correspond to a known line activity, fault type, or fault location. A disruption or parameter value pattern is classified through statistical inference of operational and performance data collected from the line. Where the disruption and/or parameter value(s) correlate with a time the customer is at the customer premises, an inference is made that the line fault causing the disruption is more likely at the CPE than at the Central Office. Where the disruption distribution is classified as being a result of human activities initiated on the line, a fault condition associated with the activity is inferred. Where a disruption pattern is correlated with human initiated plain old telephone service (POTS), a micro-filter problem is inferred for the line.