International Business Machines Corporation

Ecophysics Ag

Steven G Barbee

Leping Li

Tony F Heinz

Eugene Henry Ratzlaff

Arnold Halperin

Yiping Hsiao

Justin W Wong

Richard Anthony Conti

Victor J Silvestri

Narayana V Sarma

Steven Paul Zuhoski

Donald Leslie Wilson

Jing James Xu

Xue Ying Zhang

Si Er Han

Ji Hui Yang

Jonathan Daniel Chapple-Sokol

Cong Wei

Justin Wai-Chow Wong

Richard Hsiao

Xinhui Wang

Madhav Datta

James Anthony O'Neill

James Albert Gilhooly

Ravindra V Shenoy

William J Patrick

Scott R Cline

Justin Wai-chow Wong

Alexander Kostenko

Gregory P Devine

Gerard Seeley

Da-Yuan Shih

Wesley Charles Natzle

Viorel C Ontalus

David Edward Kotecki

Charles Hampton Perry

James Marc Leas

Seshadri Subbanna

Louis DeWolf Lanzerotti

Basanth Jagannathan

Ryan Wayne Wuthrich

George E Stark

David C Ahlgren

Jae M Park

Marc Waine Cantell

Richard John Lebel

Jungihl Kim

Eric James Lee

Rock Nadeau

Hung-Chang W Huang

James R Lloyd

William Joseph Surovic

Walter Imfeld

Gary R Doyle

Werner Moser

Donald J Hunt

Arunachala Nagarajan

Anne Elizabeth McGuire

Jeong Woo Nam

Robert B Lipori

Francisco Agustin Martin

Benjamin R Chu

John W Hopkins

Richard Mars Ruggiero

William Joseph Surovie

Yogesh P Badhe

Yuusheng Song

Adrian Siegrist

Heinz Stunzi

Ulrich Hofer

Michael J Balconi-Lamica

Francis Walter Kazak

Kevin L Holland

Embodiments of the present disclosure relate to a method, system, and computer program product for efficient execution of a decision tree. According to the method, respective target values of a plurality of attributes of a target entity are obtained. Representations of a plurality of leaf nodes of a decision tree are obtained. Each of the representations indicates respective statistic values of a plurality of attributes of historical entities and a statistic prediction result determined from historical prediction results output at a respective one of the plurality of leaf nodes for the historical entities. Distance measures between the target entity and the plurality of leaf nodes are determined based on the target values and the statistic values indicated by the representations of the plurality of leaf nodes. A target prediction result for the target entity is determined based on the distance measures and the statistic prediction results of the historical entities.

Efficient execution of a decision tree

A method includes training a plurality of different types of machine learning models using a training dataset to produce a set of trained machine learning models and determining a lift of each trained machine learning model in the set of trained machine learning models using a validation dataset. The method also includes selecting a trained machine learning model from the set of trained machine learning models that has a highest lift of the set of trained machine learning models and predicting a likelihood that a person will perform an action by applying the selected trained machine learning model to data about the person.

Uplift modeling

A computer-implemented method, system and computer program product for improving prediction accuracy in machine learning techniques. A teacher model is constructed, where the teacher model generates a weight for each data case. The current student model is then trained using training data and the weights generated by the teacher model. After training the current student model, the current student model generates state features, which are used by the teacher model to generate new weights. A candidate student model is then trained using training data and these new weights. A reward is generated by comparing the current student model with the candidate student model using training and testing data, which is used to update the teacher model if a stopping rule has not been satisfied. Upon a stopping rule being satisfied, the weights generated by the teacher model are deemed to be the 'optimal' weights which are returned to the user.

Identifying optimal weights to improve prediction accuracy in machine learning techniques

An approach for prioritizing work requests to resolve incidents in an information technology (IT) infrastructure is presented. Historical data of work requests to resolve incidents in the IT infrastructure is divided into first and second data sets. A first set of data fields of work requests in the first data set is used to generate incident concept(s). The incident concept(s) are combined with a second set of data fields of the work requests in the first data set to form a set of predictive variables. Utilizing the predictive variables, a statistical model is generated for predicting whether or not work requests will be resolved in accordance with a service level target. The statistical model is validated using the second data set. The statistical model is deployed to the IT infrastructure.

Predicting service request breaches

Embodiments of the invention may be used to produce a data mining signal by generating hybrid dataset representing data related to tools used during a semiconductor fabrication process. By selectively combining similar processes, the data mining signal strength of each tool used to perform the steps of the fabrication process may be increased. A combined process variable may be used to represent the group of tools and processes, collectively. A set of rules may be composed to determine which processes used in the semiconductor fabrication process should be combined in the hybrid dataset.

Combined feature creation to increase data mining signal in hybrid datasets

Dimensional data with attributed categorical variables is mined against a continuous target with any data mining method by ranking variables. The ranked variables are used to generate a tree. A population and a target value, obtained from a top node of the tree, are stored. The top node is removed from the tree to create a new tree with a next top node. Obtaining and storing a next population and a next target value for the next top node, and removing the top node or top field to create a new tree, are repeated. The listing of sequential top node parameters is plotted on a tree cusp curve that provides a graphical user interface enabling identification of a field which affect a greatest or a least number of records, based upon a magnitude of departure of the field from a norm.

Data mining using variable rankings and enhanced visualization methods

An exemplary method for performing fabrication sequence analysis, the method comprising, defining a process group, wherein a process group includes fabrication processes in a fabrication sequence, determining fabrication process paths in the process group to define independent variables, wherein a process path is a plurality of fabrication equipment used to fabricate a particular semiconductor device in the fabrication sequence, receiving a dependent variable for the fabrication sequence, performing analysis of variance to calculate a p-value for the process group, determining whether the p-value is lower than a threshold value, identifying a poor process path responsive to determining that the p-value is lower than a threshold value, and outputting the identified poor process path.

Methods of fabricating optimization involving process sequence analysis

Improved endpoint detection is obtained for wet etch and/or other chemical processes involving in situ measurement of bath impedance. The endpoint detection uses a measurement apparatus having a measurement circuit with a capacitor designed to alter the phase angle of the circuit. The capacitor is preferably a variable capacitor which is used to set the initial phase angle of the measurement circuit to about zero. The methods using the improved detection enable etch to be more precisely controlled even under conditions where noise would otherwise adversely impact determination of the endpoint.

Enhanced endpoint detection for wet etch process control

An apparatus for measuring ammonia gas concentration in an ongoing chemical mechanical polishing (CMP) cycle utilizing an acidic CMP slurry, having the following components:

Apparatus for detecting CMP endpoint in acidic slurries

An apparatus for measuring ammonia gas concentration in an ongoing mechanical polishing (CMP) cycle utilizing an acidic CMP slurry, having the following components:

Method for detecting CMP endpoint in acidic slurries

An oxide etch process is described which may be used for emitter and base preparation in bipolar SiGe devices. The low temperature process employed produces electrical insulation between the emitter and base by a COR etch which preserves insulating TEOS glass. The insulating TEOS glass provides reduced capacitance and helps to achieve high speed. An apparatus is also described for practicing the disclosed process.

Low defect pre-emitter and pre-base oxide etch for bipolar transistors and related tooling

A method is described for fabricating a cloisonn&eacute; structure, in which a top surface of a metal oxide layer is made coplanar with a top surface of a metallic structure formed on a substrate. A nitride layer is deposited on at least the top surface of the metallic structure, and the metal oxide layer is deposited over the metallic structure and the nitride layer. The metal oxide layer is then polished by a chemical-mechanical polishing (CMP) process using a slurry, to expose the nitride layer on the top surface of the metallic structure. Polishing of the nitride layer causes ammonia to be generated in the slurry. The ammonia is extracted as a gas from the slurry, and a signal is generated in accordance with the ammonia concentration. The CMP process is terminated in accordance with a change in the signal. In a preferred embodiment, the metal oxide is aluminum oxide, the nitride is aluminum nitride, and the nitride layer is deposited as a conformal layer on the substrate and the metallic structure.

Endpoint detection in chemical-mechanical polishing of cloisonne structures

The change in thickness of a film on an underlying body such as a semiconductor substrate is monitored in situ by inducing a current in the film, and as the thickness of the film changes (either increase or decrease), the changes in the current are detected. With a conductive film, eddy currents are induced in the film by a generating an alternating electromagnetic field with a sensor which includes a capacitor and an inductor.

In-situ monitoring and control of conductive films by detecting changes

A contactless method and apparatus for real-time in-situ monitoring of a chemical etching process during etching of at least one wafer in a wet chemical etchant bath are disclosed. The method comprises the steps of providing two conductive electrodes in the wet chemical bath, wherein the two electrodes are proximate to but not in contact with a wafer; monitoring an electrical characteristic between the two electrodes as a function of time in the etchant bath of the at least one wafer, wherein a prescribed change in the electrical characteristic is indicative of a prescribed condition of the etching process; and recording a plurality of values of the electrical characteristic as a function of time during etching. From the plurality of recorded values and corresponding times, instantaneous etch rates, average etch rates, and etching end points may be determined. Such a method and the apparatus therefor are particularly useful in a wet chemical etch station.

Real time measurement of etch rate during a chemical etching process

Growing community of inventors

Dover Plains, NY, United States of America

Steven G Barbee