OML feature highlight: Time Series analysis with Oracle Machine Learning

On this weekly Office Hours for Oracle Machine Learning on Autonomous Database, Bhoopendra Singh, Implementation Specialist - DWH, Lake, Analytics, Data Science and AI presented the concepts about the Time Series algorithms available in Oracle Database, and will do a Live Demo on OML Notebooks.

The Oracle Machine Learning product family supports data scientists, analysts, developers, and IT to achieve data science project goals faster while taking full advantage of the Oracle platform.

The Oracle Machine Learning Notebooks offers an easy-to-use, interactive, multi-user, collaborative interface based on Apache Zeppelin notebook technology, and support SQL, PL/SQL, Python and Markdown interpreters. It is available on all Autonomous Database versions and Tiers, including the always-free editions.

OML includes AutoML, which provides automated machine learning algorithm features for algorithm selection, feature selection and model tuning, in addition to a specialized AutoML UI exclusive to the Autonomous Database.

OML Services is also included in Autonomous Database, where you can deploy and manage native in-database OML models as well as ONNX ML models (for classification and regression) built using third-party engines, and can also invoke cognitive text analytics.

Transcript

1. OML feature highlight:
   Time Series analysis with Oracle Machine Learning
   OML Office Hours
   Bhoopendra Singh
   Implementation Specialist - DWH, Lake, Analytics, Data Science and AI
   Supported by Marcos Arancibia, Mark Hornick and Sherry LaMonica
   Product Management, Oracle Machine Learning
   Move the Algorithms; Not the Data!
   Copyright © 2021, Oracle and/or its affiliates.
   This Session will
   be Recorded
   

   View Slide

2. • Upcoming Sessions
   • Time Series analysis with Oracle Machine Learning
   • Q&A
   Topics for today
   Copyright © 2021, Oracle and/or its affiliates
   2
   

   View Slide

3. November 16 2021 08:00 AM Pacific
   • Weekly Office Hours: OML on Autonomous Database - Ask & Learn
   November 9 2021 08:00 AM Pacific
   • OML Usage Highlight: Leveraging OML algorithms in Retail Science platform – Fraud Detection
   • Oracle Retail XBRi Loss Prevention solution flags outlier cashier behavior or outlier customer
   behavior using OML models, and can deliver the information to the retailer for further investigation.
   Upcoming Sessions
   Copyright © 2021, Oracle and/or its affiliates
   3
   

   View Slide

4. ORACLE MACHINE LEARNING
   TIME SERIES FORECASTING
   Bhoopendra Singh
   Implementation Specialist Lift Services
   Analytics & Machine Learning
   

   View Slide

5. Agenda
   5 Copyright © 2020, Oracle and/or its affiliates
   § Time Series
   § Time Series Patterns
   § Exponential Smoothing
   § Demo
   § Q/A
   

   View Slide

6. Time Series
   Copyright © 2020, Oracle and/or its affiliates
   6
   Time series forecasting is a technique for the prediction of events through a sequence of time.
   The techniques predict future events by analyzing the trends of the past, on the assumption that
   future trends will hold similar to historical trends . It is a specialized form of Regression, known in
   the literature as auto-regressive modeling.
   In OML
   • The input to time series analysis is a sequence of target values. A case id column specifies the
   order of the sequence.
   • The time series model provide estimates of the target value for each step of a time window that
   can include up to 30 steps beyond the historical data.
   • Oracle Machine Learning provides Exponential Smoothing Algorithm for predicting Time
   series Models.
   • Oracle time series analysis handles irregular time series.
   

   View Slide

7. Time Series Patterns
   Copyright © 2020, Oracle and/or its affiliates
   7
   Trend : A trend exists when there is a long-term increase
   or decrease in the data. It does not have to be linear.
   Seasonality: A seasonal pattern occurs when a time
   series is affected by seasonal factors such as the time of
   the year or the day of the Week.
   Cyclic : A cycle occurs when the data exhibit rises and
   falls that are not of a fixed frequency.
   Noise : Noise is the completely random fluctuation
   present in the data and we cannot use this component
   to forecast into the future
   

   View Slide

8. Exponential Smoothing
   Copyright © 2020, Oracle and/or its affiliates
   8
   Exponential Smoothing is a moving average method with a single parameter which models an exponentially
   decreasing effect of past levels on future values.
   Exponential Smoothing is extended to the following:
   • A matrix of models that mix and match error type (additive or multiplicative), trend (additive, multiplicative,
   or none), and seasonality (additive, multiplicative, or none)
   • Models with damped trends.
   • Models that directly handle irregular time series and time series with missing values.
   

   View Slide

9. Exponential Smoothing
   Copyright © 2020, Oracle and/or its affiliates
   9
   Simple Exponential Smoothing Simple Exponential Smoothing assumes the data fluctuates around a
   stationary mean, with no trend or seasonal pattern.
   In simple exponential smoothing model, each forecast (smoothed value) is computed as the weighted
   average of the previous observations, where the weights decrease exponentially depending on the value of
   smoothing constant α.
   

   View Slide

10. Exponential Smoothing
    Copyright © 2020, Oracle and/or its affiliates
    10
    Models with Trend but No Seasonality The preferred form of additive (linear) trend is sometimes called Holt’s
    method or double exponential smoothing.
    Models with trend add a smoothing parameter γ and optionally a damping parameter φ. The damping
    parameter smoothly dampens the influence of past linear trend on future estimates of level, often improving
    accuracy.
    

    View Slide

11. Exponential Smoothing
    Copyright © 2020, Oracle and/or its affiliates
    11
    Models with Seasonality but No Trend When the time series average does not change over time (stationary),
    but is subject to seasonal fluctuations, the appropriate model has seasonal parameters but no trend.
    Seasonal fluctuations are assumed to balance out over periods of length m, where m is the number of
    seasons, For example, m=4 might be used when the input data are aggregated quarterly
    

    View Slide

12. Exponential Smoothing
    Copyright © 2020, Oracle and/or its affiliates
    12
    Models with Trend and Seasonality Holt and Winters introduced both trend and seasonality in Exponential
    Smoothing Model(ESM). The original model, also known as Holt-Winters or triple exponential smoothing,
    considered an additive trend and multiplicative seasonality.
    Extensions include models with various combinations of additive and multiplicative trend, seasonality and
    error, with and without trend damping.
    

    View Slide

13. Demo: Forecasting Sales Using Exponential Smoothing
    Algorithm for Time Series Data
    Copyright © 2020, Oracle and/or its affiliates
    13
    

    View Slide

14. Q & A
    Copyright © 2021, Oracle and/or its affiliates
    14
    

    View Slide

15. Thank you
    Boopendra.singh@oracle.com
    Copyright © 2021, Oracle and/or its affiliates.
    15
    

    View Slide