# US 2023/0409901 A1 · Systems and methods for time series forecasting

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0409901 A1
- Document ID: US20230409901A1
- Status: Published application
- Kind: A1
- Application number: 17/946,363
- Filed: 2022-09-16
- Published: 2023-12-21
- Earliest claimed: 2022-05-20
- Assignees: Salesforce, Inc.
- Applicants: Salesforce, Inc.
- Inventors: Chenghao Liu; Chu Hong Hoi; Kun Zhang
- Web page: https://patentgrep.com/patent/US20230409901A1

## CPC

- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/047: Probabilistic or stochastic networks
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods for providing a neural network system for time series forecasting are described. A time series dataset that includes datapoints at a plurality of timestamps in an observed space is received. The neural network system is trained using the time series dataset. The training the neural network includes: generating, using an encoder of the neural network system, one or more estimated latent variables of a latent space for the time series dataset; generating, using an auxiliary predictor of the neural network system, a first latent-space prediction result based on the one or more estimated latent variables; transforming, using a decoder of the neural network system, the first latent-space prediction result to a first observed-space prediction result; and updating parameters of the neural network system based on a loss based on the first observed-space prediction result.

## Claims

### Claim 1

A method of providing a neural network system for time series forecasting, comprising:
receiving, via an input interface, a time series dataset that includes datapoints at a plurality of timestamps in an observed space;
training the neural network system using the time series dataset, wherein the training the neural network system includes:
generating, using a first encoder of the neural network system, one or more estimated latent variables of a latent space for the time series dataset;
generating, using an auxiliary predictor of the neural network system, a first latent-space prediction result based on the one or more estimated latent variables;
transforming, using a first decoder of the neural network system, the first latent-space prediction result to a first observed-space prediction result; and
updating parameters of the neural network system using a first objective based on the first latent-space prediction result and the first observed-space prediction result.

### Claim 2 (depends on 1)

The method of claim 1, wherein each of the latent variables is identifiable from a corresponding observed data.

### Claim 3 (depends on 1)

The method of claim 1, wherein the one or more estimated latent variables are determined based on one or more estimated time-varying change factors.

### Claim 4 (depends on 3)

The method of claim 3, wherein the training the neural network system includes:
providing, using the auxiliary predictor, a first estimated noise based on the one or more estimated latent variables and the one or more estimated time-varying change factor; and
generating, using the auxiliary predictor, the first latent-space prediction result based on the one or more estimated latent variables and the first estimated noise.

### Claim 5 (depends on 1)

The method of claim 1, wherein the neural network system includes a variational autoencoder (VAE) including the first encoder and the first decoder, and
wherein the first objective includes an augmented evidence lower bound (ELBO) objective.

### Claim 6 (depends on 1)

The method of claim 1, wherein the first objective is based on an auxiliary predictor distribution associated with the first latent-space prediction result.

### Claim 7 (depends on 1)

The method of claim 1, wherein the one or more estimated latent variables are generated based on a non-parametric state space model for a dynamical system underlying time series dataset.

### Claim 8

A non-transitory machine-readable medium comprising a plurality of machine-readable instructions which, when executed by one or more processors, are adapted to cause the one or more processors to perform a method comprising:
receiving, via an input interface, a time series dataset that includes datapoints at a plurality of timestamps in an observed space;
training a neural network system using the time series dataset, wherein the training the neural network system includes:
generating, using a first encoder of the neural network system, one or more estimated latent variables of a latent space for the time series dataset;
generating, using an auxiliary predictor of the neural network system, a first latent-space prediction result based on the one or more estimated latent variables;
transforming, using a first decoder of the neural network system, the first latent-space prediction result to a first observed-space prediction result; and
updating parameters of the neural network system using a first objective based on the first latent-space prediction result and the first observed-space prediction result.

### Claim 9 (depends on 8)

The non-transitory machine-readable medium of claim 8, wherein each of the latent variables is identifiable from a corresponding observed data.

### Claim 10 (depends on 8)

The non-transitory machine-readable medium of claim 8, wherein the one or more estimated latent variables are determined based on one or more estimated time-varying change factors.

### Claim 11 (depends on 10)

The non-transitory machine-readable medium of claim 10, wherein the training the neural network system includes:
providing, using the auxiliary predictor, a first estimated noise based on the one or more estimated latent variables and the one or more estimated time-varying change factor; and
generating, using the auxiliary predictor, the first latent-space prediction result based on the one or more estimated latent variables and the first estimated noise.

### Claim 12 (depends on 8)

The non-transitory machine-readable medium of claim 8, wherein the neural network system includes a variational autoencoder (VAE) including the first encoder and the first decoder, and
wherein the first objective includes an augmented evidence lower bound (ELBO) objective.

### Claim 13 (depends on 8)

The non-transitory machine-readable medium of claim 8, wherein the first objective is based on an auxiliary predictor distribution associated with the first latent-space prediction result.

### Claim 14 (depends on 8)

The non-transitory machine-readable medium of claim 8, wherein the one or more estimated latent variables are generated based on a non-parametric state space model for a dynamical system underlying time series dataset.

### Claim 15

A system, comprising:
a non-transitory memory; and
one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform a method comprising:
receiving, via an input interface, a time series dataset that includes datapoints at a plurality of timestamps in an observed space;
training a neural network system using the time series dataset, wherein the training the neural network system includes:
generating, using a first encoder of the neural network system, one or more estimated latent variables of a latent space for the time series dataset;
generating, using an auxiliary predictor of the neural network system, a first latent-space prediction result based on the one or more estimated latent variables;
transforming, using a first decoder of the neural network system, the first latent-space prediction result to a first observed-space prediction result; and
updating parameters of the neural network system using a first objective based on the first latent-space prediction result and the first observed-space prediction result.

### Claim 16 (depends on 15)

The system of claim 15, wherein each of the latent variables is identifiable from a corresponding observed data.

### Claim 17 (depends on 15)

The system of claim 15, wherein the one or more estimated latent variables are determined based on one or more estimated time-varying change factors.

### Claim 18 (depends on 16)

The system of claim 16, wherein the training the neural network system includes:
providing, using the auxiliary predictor, a first estimated noise based on the one or more estimated latent variables and the one or more estimated time-varying change factor; and
generating, using the auxiliary predictor, the first latent-space prediction result based on the one or more estimated latent variables and the first estimated noise.

### Claim 19 (depends on 15)

The system of claim 15, wherein the neural network system includes a variational autoencoder (VAE) including the first encoder and the first decoder, and
wherein the first objective includes an augmented evidence lower bound (ELBO) objective.

### Claim 20 (depends on 15)

The system of claim 15, wherein the first objective is based on an auxiliary predictor distribution associated with the first latent-space prediction result.
