API Reference - Models
If you wonder what are the most high-value use cases that helps with retention and revenue generation with this DataPredict™, you can view them here!
| Model Type | Count |
|---|---|
| Regression | 5 |
| Classification | 13 |
| Clustering | 8 |
| Deep Reinforcement Learning | 21 |
| Tabular Reinforcement Learning | 5 |
| Generative | 4 |
| Total | 57 |
For strong deep learning applications, have a look at DataPredict™ Neural (object-oriented) and DataPredict™ Axon (function-oriented) instead.
-
Contains all the deep reinforcement learning and generative algorithms listed here.
-
Includes convolutional, pooling, embedding, dropout and activation layers.
-
Uses reverse-mode automatic differentiation for DataPredict™ Neural (static graph) and DataPredict™ Axon (dynamic graph).
Note
Currently, these algorithms lack online learning capabilities. We’re still looking into it.
| Model Type | Model Names |
|---|---|
| Regression | NormalLinearRegression, SupportVectorRegression |
| Classification | SupportVectorMachine, OneClassSupportVectorMachine |
| Clustering | KMedoids, AffinityPropagation, DensityBasedSpatialClusteringOfApplicationsWithNoise |
This means DataPredict™ has ~90% (50 out of 57) models with online learning capabilities.
By default, most models would perform offline / batch training on the first train, but then switches to online / sequential / incremental after the first train.
Regression
| Model | Alternate Names | Use Cases |
|---|---|---|
| LinearRegression (Beginner Algorithm) | None | General Time-To-Leave Prediction And In-Game Currency Price Generation |
| PassiveAggressiveRegressor | PA-R | Fast Constrained Time-To-Leave Prediction And In-Game Currency Price Generation |
| SupportVectorRegression | SVR | Constrained Time-To-Leave Prediction And In-Game Currency Price Generation |
| KNearestNeighboursRegressor | KNN-R | Memory-Based Time-To-Leave Prediction And In-Game Currency Price Generation |
| NormalLinearRegression (Not Recommended) | None | Final Solution Time-To-Leave Prediction And In-Game Currency Price Generation |
Classification
| Model | Alternate Names | Use Cases |
|---|---|---|
| LogisticRegression (Beginner Algorithm) | Perceptron | Probability-To-Leave Prediction, Player Churn Prediction, Confidence Prediction |
| PassiveAggressiveClassifier | PA-C | Fast Purchase Likelihood Estimation, Decision Making |
| OneClassPassiveAggressiveClassifier | OC-PA-C | Fast Hacking Detection, Anomaly Detection (Using Single Class Data) |
| NearestCentroid | NC | Fast Grouping Or Quick Decision Making |
| KNearestNeighboursClassifier | KNN-C | Item Recommendation, Similar Player Matchmaking |
| SupportVectorMachine | SVM | Hacking Detection, Anomaly Detection |
| OneClassSupportVectorMachine | OC-SVM | Hacking Detection, Anomaly Detection (Using Single Class Data) |
| NeuralNetwork (Beginner Algorithm) | Multi-Layer Perceptron | Decision-Making, Player Behaviour Prediction |
| GaussianNaiveBayes (Stonger As Generative Model) | None | Player Behavior Categorization (e.g. Cautious Vs. Aggressive), Fast State Classification |
| MultinomialNaiveBayes (Stonger As Generative Model) | None | Inventory Action Prediction, Strategy Profiling Based on Item Usage |
| BernoulliNaiveBayes (Stonger As Generative Model) | None | Binary Action Prediction (e.g. Jump Or Not), Quick Decision Filters |
| ComplementNaiveBayes (Stonger As Generative Model) | None | Imbalanced Class Prediction (e.g. Rare Choices, Niche Paths) |
| CategoricalNaiveBayes (Stonger As Generative Model) | None | Player Choice Prediction (e.g. Weapon Type, Character Class, Map Region Selection) |
Clustering
| Model | Alternate Names | Use Cases |
|---|---|---|
| KMeans (Beginner Algorithm) | None | Maximizing Area-of-Effect Abilities, Target Grouping |
| FuzzyCMeans | None | Overlapping Area-of-Effect Abilities, Overlapping Target Grouping |
| KMedoids | None | Player Grouping Based On Player Locations With Leader Identification |
| AgglomerativeHierarchical | None | Enemy Difficulty Generation |
| ExpectationMaximization | EM | Hacking Detection, Anomaly Detection |
| MeanShift | None | Boss Spawn Location Search Based On Player Locations |
| AffinityPropagation | None | Player Grouping |
| DensityBasedSpatialClusteringOfApplicationsWithNoise | DBSCAN | Density Grouping |
Deep Reinforcement Learning
| Model | Alternate Names | Use Cases |
|---|---|---|
| DeepQLearning | Deep Q Network | Best Self-Learning Player AIs, Best Recommendation Systems |
| DeepDoubleQLearningV1 | Double Deep Q Network (2010) | Best Self-Learning Player AIs, Best Recommendation Systems |
| DeepDoubleQLearningV2 | Double Deep Q Network (2015) | Best Self-Learning Player AIs, Best Recommendation Systems |
| DeepClippedDoubleQLearning | Clipped Deep Double Q Network | Best Self-Learning Player AIs, Best Recommendation Systems |
| DeepStateActionRewardStateAction | Deep SARSA | Safe Self-Learning Player AIs, Safe Recommendation Systems |
| DeepDoubleStateActionRewardStateActionV1 | Double Deep SARSA | Safe Self-Learning Player AIs, Safe Recommendation Systems |
| DeepDoubleStateActionRewardStateActionV2 | Double Deep SARSA | Safe Self-Learning Player AIs, Safe Recommendation Systems |
| DeepExpectedStateActionRewardStateAction | Deep Expected SARSA | Balanced Self-Learning Player AIs, Balanced Recommendation Systems |
| DeepDoubleExpectedStateActionRewardStateActionV1 | Double Deep Expected SARSA | Balanced Self-Learning Player AIs, Balanced Recommendation Systems |
| DeepDoubleExpectedStateActionRewardStateActionV2 | Double Deep Expected SARSA | Balanced Self-Learning Player AIs, Balanced Recommendation Systems |
| DeepMonteCarloControl (May Need Further Refinement) | None | Online Self-Learning Player AIs |
| DeepOffPolicyMonteCarloControl | None | Offline Self-Learning Player AIs |
| REINFORCE | None | Reward-Based Self-Learning Player AIs |
| VanillaPolicyGradient (May Need Further Refinement) | VPG | Baseline-Based Self-Learning Player AIs |
| ActorCritic | AC | Critic-Based Self-Learning Player AIs |
| AdvantageActorCritic | A2C | Advantage-Based Self-Learning Player AIs |
| ProximalPolicyOptimization | PPO | Industry-Grade And Research-Grade Self-Learning Player And Vehicle AIs |
| ProximalPolicyOptimizationClip | PPO-Clip | Industry-Grade And Research-Grade Self-Learning Player And Vehicle AIs |
| SoftActorCritic | SAC | Self-Learning Vehicle AIs |
| DeepDeterministicPolicyGradient | DDPG | Self-Learning Vehicle AIs |
| TwinDelayedDeepDeterministicPolicyGradient | TD3 | Self-Learning Vehicle AIs |
Tabular Reinforcement Learning
| Model | Alternate Names | Use Cases |
|---|---|---|
| TabularQLearning | Q-Learning | Best Self-Learning Grid AIs |
| TabularStateActionRewardState (May Need Further Refinement) | SARSA | Safe Self-Learning Grid AIs |
| TabularExpectedStateActionRewardState | Expected SARSA | Balanced Self-Learning Grid AIs |
| TabularMonteCarloControl (May Need Further Refinement) | MC | Online Self-Learning Grid AIs |
| TabularOffPolicyMonteCarloControl | Off-Policy MC | Offline Self-Learning Grid AIs |
Generative
| Model | Alternate Names | Use Cases |
|---|---|---|
| GenerativeAdversarialNetwork | GAN | Enemy Data Generation |
| ConditionalGenerativeAdversarialNetwork | CGAN | Same As GAN, But Can Assign Classes |
| WassersteinGenerativeAdversarialNetwork | WGAN | Same As GAN, But More Stable |
| ConditionalWassersteinGenerativeAdversarialNetwork | CWGAN | Combination Of Both CGAN And WGAN |
BaseModels
DeepReinforcementLearningBaseModel