Problem Types and Algorithms supported

The Problem Type defines the category of the machine learning task. This selection helps the system choose the right algorithms, preprocessing steps, and evaluation metrics.

The available problem types are:

  1. Classification – Predicts categories or labels (e.g., spam or not spam). Logistic Regression, Naive Bayes, Decision Tree, Random Forest, Support Vector Machine, K Nearest Neighbors, Gradient Boosting, Extreme Gradient Boosting, Light Gradient Boosting, Categorical Boosting, Bagging)
  2. Regression – Predicts continuous values (e.g., price of a house).(Extreme Gradient Boosting, Light Gradient Boosting, Categorical Boosting, Bagging, Random Forest, Lasso, Ridge, Linear Regression, Decision tree)
  3. Time Series Forecasting – Predicts future values based on historical time-based data. (ARIMA, ARIMA WITH GARCH, VAR, FBPROPHET, MLP, LSTM, EWMA)
  4. Clustering – Groups data points into similar categories without using a target variable. (K-Means , DB Scan)
  5. Document Similarity – Compares how similar two or more text documents are.(TF -IDF, TF- IDF(SVD))
  6. Anomaly Detection – Identifies unusual patterns or outliers in the data. It also supports Timeseries Anomaly Detection. (Isolation Forest, OneclassSVM, DBScan, Zscore)
  7. Graph Analytics - analyzing relationships, community structures, and network patterns.(NetworkX)
  8. Recommender System -Support recommendation models. (Item Rating, Association Rules – Apriori)

HCL AION automatically analyzes your uploaded dataset and recommends the most suitable problem type based on the characteristics of your data.