The hmix algorithm models time-dependent sequences by identifying hidden states using a Hidden Markov Model (HMM) and clustering techniques like k-means. It forecasts future sequences by fitting multiple distributions and evaluating their accuracy through backtesting with CRPS.

Spinner is a torch implementation enabling the use of Graph Nets in R-based machine learning workflows.

Estimating your potential market space using GNN (Graph Neural Networks) can be improved by gathering relevant data, choosing the appropriate GNN model, preprocessing and normalizing the data, using visualization tools, and considering additional factors.

Proteus is a Sequence-to-Sequence Variational Model designed for time-feature analysis, leveraging a wide range of distributions for improved accuracy.

janus is a coarse-to-fine optimization for a recommending system based on embedding neural networks

Seq2seq Time-Feature Analysis using an Encoder-Decoder to project into latent space and a Forward Network to predict the next sequence, based on Tensorflow.

segen is a model for sequence generalization using the “network” of similarities among sequences for the extrapolation

Naive is a model to extract the common patterns from sequences and extrapolate time features

dymo proposes an implementation of Dynamic Mode Decomposition (SVD-approach) to predict multiple time features

Dynamic regression for time series using Extreme Gradient Boosting with hyper-parameter tuning via Bayesian Optimization or Random Search.

Automatic fast extrapolation of time features using kNN.

Time features extrapolation through spectral analysis and jack-knife resampling.

Model for sequence forecasting based on expansion of distance matrix.

SNAP is a tool to design deep neural network with a single line of code.