Systems and methods for network performance forecasting

A system comprising:

• a computer data repository that stores historical performance data for a cell in a network;
• a second computer data repository that stores baseline data for the cell in the network;
• a computing system comprising one or more computing devices, the computing system in communication with the computer data repository, the computing system programmed to implement:
• a historical performance data collection unit configured to receive the historical performance data and the baseline data, the historical performance data comprising a plurality of key performance indicators (KPIs);
• and
• a network forecast determination unit configured to receive a selection of a first KPI in the plurality of KPIs, the network forecast determination unit further configured to:
• apply a machine learning model to at least the first KPI and a second KPI in the plurality of KPIs to identify a relationship between the first KPI and the second KPI,
• apply the machine learning model to the first KPI and a third KPI in the plurality of KPIs to identify a second relationship between the first KPI and the third KPI,
• determine that a correlation between the first KPI and the third KPI is greater than a threshold correlation value based on the identified second relationship,
• generate a first model parameter based on the identified relationship between the first KPI and the second KPI,
• generate a second model parameter based on the identified second relationship between the first KPI and the third KPI in response to the determination that the correlation between the first KPI and the third KPI is greater than the threshold correlation value,
• apply the baseline data to the first model parameter and the second model parameter, and
• calculate a predicted value of the first KPI for the cell in the network based on the application of the baseline data to the first model parameter and the second model parameter.

A computer storage system comprising a non-transitory storage device, said computer storage system having stored thereon executable program instructions that direct a computer system to at least:

• access historical performance data and baseline data for a cell in a telecommunications network, the historical performance data comprising a plurality of key performance indicators (KPIs);
• electronically output a graphical user interface for presentation to a user, the graphical user interface comprising functionality for the user to select one or more of the KPIs;
• receive, from the graphical user interface, a user selection of a first KPI of the plurality of KPIs;
• apply a machine learning model to the first KPI and a second KPI in the plurality of KPIs to identify a relationship between the first KPI and the second KPI;
• apply the machine learning model to the first KPI and a third KPI in the plurality of KPIs to identify a second relationship between the first KPI and the third KPI;
• determine that a correlation between the first KPI and the third KPI is greater than a threshold correlation value based on the identified second relationship;
• generate a first model parameter based on the identified relationship between the first KPI and the second KPI;
• generate a second model parameter based on the identified second relationship between the first KPI and the third KPI in response to the determination that the correlation between the first KPI and the third KPI is greater than the threshold correlation value;
• apply the baseline data to the first model parameter and the second model parameter;
• calculate a predicted value of the first KPI for the cell in the telecommunications network based on the application of the baseline data to the first model parameter and the second model parameter;
• and
• output a representation of the predicted value of the first KPI for presentation to the user.