How AI features works:

Shoplogix uses advanced algorithms ( time series analysis, correlations, decision tree ) and machine learning techniques to automatically analyze data and identify patterns, trends, and correlations.

Insight Miner also analyzes the schema and statistics of your tables to understand the relationships and distributions within the data ( including removing outliers, missing value imputation, feature selection, and statistical tests ) this allows it to make intelligent recommendations

Shoplogix uses “Knowledge Graph” algorithm to organize information in structured way to show how different data/features are connected and related.

The knowledge graph technique also actively learns, registering when the user chooses to accept a recommendation, and ultimately delivering more personalized suggestions.

Using this algorithm Explanations feature analyzes all possible factors that have influenced the change in a selected point in a data set, compared to a different point (for time based widgets) or that contribute to a KPI (for indicator widgets). Explanations then displays the most probable explaining fields, ranked by their contribution.

Shoplogix uses "Ensemble" as the default forecasting method.

"Ensemble"uses a machine-learning powered calculation that automatically runs 4 different models (Auto Arima, Prophet, Holt-Winters, and Random Forest techniques) on the historical data, compares their output with the actual historical results, and selects the model, or blend of models, that best suits the specific dataset to create the forecast.

Shoplogix uses an AI algorithm that runs behind the scenes, analyzing how users interact with the dashboard. As time goes on, the AI gets better at this by learning from more user activity.

The AI examines all the unique ways users combine information. It then uses a clever math concept called the ” Fuzzy Jaccard Similarity coefficient” to measure how much your chosen formulas/widgets are like others in a dashboard. This gives a score that shows how similar they are.

The AI also uses something called “Pointwise Mutual Information (PMI)” to figure out which data points are often seen together in similar formulas/widgets. PMI is like a measure of teamwork between data points. It ranks these data points by how often they team up.

The outcome is a ranked list of data points that frequently go along with formulas/widgets. The AI suggests the top-ranking data points as widgets for further exploration. This adds more insights to your data, helping you uncover valuable information.