International Business Machines Corporation

Jiang Bo Kang

Dong Hai Yu

Yao Dong Liu

Jun Wang

Song Bo

Bo Song

Jun Song Wang

Xiao Ming Ma

Jing James Xu

Lei Tian

Xing Wei

Rui Wang

One or more computer processors calculate a cache prediction for a received inference request within an inference cache structured as a self-learning tree, wherein the inference request comprises a set of input values. The one or more computer processors responsive to the retrieved cache prediction exceeding a cache prediction threshold, transmit the cache prediction. The one or more computer processors parallel compute a model prediction for the received inference request utilizing a trained model. The one or more computer processors responsive to the retrieved model prediction exceeding a model prediction threshold, convert the trained model into a tree structure. The one or more computer processors update the inference cache with the converted train model. The one or more computer processors transmit the model prediction.

Efficient machine learning model inference

A computer-implemented system, platform, programing product, and/or method for improving transformation selection in an ensemble machine learning (ML) model that includes: providing all base ML models of the ensemble ML model; identifying all of a plurality of Derived Fields in all the base ML models; performing a Derived Field run prediction analysis for all the Derived Fields; computing the Derived Field Importance Weight for Field (DFIW4F) and the Derived Field Importance Weight for Model (DFIW4M) for all the Derived Fields; clustering all the Derived Fields into a plurality of Derived Field clusters, wherein each Derived Field cluster is based upon the DFIW4M and the DFIW4F for the Derived Field; sorting all the Derived Field clusters by best cluster based upon DFIW4M and DFIW4F; and running the base ML models based upon the Derived Fields in the best Derived Field cluster until sufficient base ML models have been run.

System and method for efficient transformation prediction in a data analytics prediction model pipeline

Systems and computer-implemented methods select a subset of methods to generate data schemas for input data from a list of methods for generating data schemas, based on output of a regression model; generate a candidate schema for each method in the subset of methods to generate data schemas; and generate a master data schema for the input data by merging the candidate schema for each method in the subset of methods to generate data schemas, utilizing predetermined rules.

Automated determination of accurate data schema

A method for forecasting server demand includes collecting a historical number of scoring requests from a network using a serverless architecture. A scoring request capacity per server is determined using the historical number of scoring requests. A prediction model predicts a first future value of scoring requests for a first future time span. A current number of servers in a pool of servers handling the scoring requests. Using the prediction model, a determination of whether the current number of servers is capable of handling the first future value of scoring requests for the first future time span is made. Upon determining that the current number of servers is incapable of handling the first future value of scoring requests, one or more additional servers are warmed up. The warmed-up additional servers are added to the pool of servers prior to an arrival of the first future time span.

Efficient serverless method and system of serving artificial intelligence models

Embodiments of the present invention disclose a method, computer program product, and system for estimating the results of a performance test on an updated software application. A method, the method comprising receiving an updated software application, wherein the size of the updated software application is a first size and generating a plurality of small probe, wherein the size of each of the small probe data is a second size, wherein the second size is less than the first size. Conducting a first performance test on the plurality of small probe data and calculating an estimated elapsed time for a performance test on the updated software application. Conducting the performance test on the updated software application and determining if the updated software is given a PASS or FAIL for the performance test, based in part on the elapsed time of the performance test on the updated software application.

Performance evaluation method using simulated probe data mapping

Described are techniques for machine learning library management. The techniques include generating a table including a plurality of machine learning libraries and their current versions that are used in a deployed machine learning platform (MLP) instance, a first available version upgrade for a first machine learning library of the plurality of machine learning libraries, a security indication associated with the first available version upgrade relative to a current version implemented by the first machine learning library, and a compatibility indication between the first available version upgrade and the current version of the first machine learning library. The techniques further include generating a recommendation related to upgrading the first machine learning library based on the security indication and the compatibility indication.

Compatible and secure software upgrades

A method for instantiating a first specific model, as one record, based on a model scoring template, clustering a plurality of models into a plurality of groups to obtain a plurality of clusters, computing a model contribution weight value for the given cluster, choosing a set of top model(s) from the plurality of models, and updating the model(s) of the set of top model(s) dynamically.

Growing community of inventors

Xi'an, China

Jiang Bo Kang