Applied Time Series Analysis and Forecasting in Python
What you'll learn
- Encounter special types of time series like White Noise and Random Walks.
- Learn about accounting for "unexpected shocks" via moving averages.
- Start coding in Python and learn how to use it for statistical analysis.
- Comprehend the need to normalize data when comparing different time series.
Requirements
- Beginner data scientists looking to gain experience with time series
- People interested in quantitative finance.
- Aspiring data scientists.
- Programmers who want to specialize in finance.
Description
How does a commercial bank forecast the expected performance of its loan portfolio?
Or how does an investment manager estimate a stock portfolio’s risk?
Which are the quantitative methods used to predict real-estate properties?
If there is some time dependency, then you know it - the answer is time series analysis.
This course will teach you the practical skills that would allow you to land a job as a quantitative finance analyst, a data analyst or a data scientist.
In no time, you will acquire the fundamental skills that will enable you to perform complicated time series analysis directly applicable in practice. We have created a time series course that is not only timeless but also:
· Easy to understand
· Comprehensive
· Practical
· To the point
· Packed with plenty of exercises and resources
But we know that may not be enough.
We take the most prominent tools and implement them through Python – the most popular programming language right now. With that in mind…
Welcome to Time Series Analysis in Python!
The big question in taking an online course is what to expect. And we’ve made sure that you are provided with everything you need to become proficient in time series analysis.
We start by exploring the fundamental time series theory to help you understand the modelling that comes afterwards.
Then throughout the course, we will work with several Python libraries, providing you with complete training. We will use the powerful time series functionality built into pandas, as well as other fundamental libraries such as NumPy, matplotlib, StatsModels, finance, ARCH and prima.
With these tools, we will master the most widely used models out there:
· AR (autoregressive model)
· MA (moving-average model)
· ARMA (autoregressive-moving-average model)
· ARIMA (autoregressive integrated moving average model)
· ARIMAX (autoregressive integrated moving average model with exogenous variables)
. SARIA (seasonal autoregressive moving average model)
. SARIMA (seasonal autoregressive integrated moving average model)
. SARIMAX (seasonal autoregressive integrated moving average model with exogenous variables)
· ARCH (autoregressive conditional heteroscedasticity model)
· GARCH (generalized autoregressive conditional heteroscedasticity model)
. VARMA (vector autoregressive moving average model)
We know that time series is one of those topics that always leaves some doubts.
Until now.
This course is exactly what you need to comprehend time series once and for all. Not only that, but you will also get a ton of additional materials – notebook files, course notes, quiz questions, and many, many exercises – everything is included.
This is the only course that combines the latest statistical and deep learning techniques for time series analysis. First, the course covers the basic concepts of time series:
stationarity and augmented Dicker-Fuller test
seasonality
white noise
random walk
autoregression
moving average
ACF and PACF,
Model selection with AIC (Akaike's Information Criterion)
Then, we move on and apply more complex statistical models for time series forecasting:
ARIMA (Autoregressive Integrated Moving Average model)
SARIMA (Seasonal Autoregressive Integrated Moving Average model)
SARIMAX (Seasonal Autoregressive Integrated Moving Average model with exogenous variables)
We also cover multiple time series forecasting with:
VAR (Vector Autoregression)
VARMA (Vector Autoregressive Moving Average model)
VARMAX (Vector Autoregressive Moving Average model with exogenous variable)
Then, we move on to the deep learning section, where we will use Tensorflow to apply different deep learning techniques for times series analysis:
Simple linear model (1-layer neural network)
DNN (Deep Neural Network)
CNN (Convolutional Neural Network)
LSTM (Long Short-Term Memory)
CNN + LSTM models
ResNet (Residual Networks)
Autoregressive LSTM
Throughout the course, you will complete more than 5 end-to-end projects in Python, with all source code available to you.
Who this course is for:
- Aspiring data scientists.
- Professional data scientists who need to analyze time series
- Deep learning beginners curious about times series
Instructor
Hello, I'm Akhil, a Senior Data Scientist at PwC specializing in the Advisory Consulting practice with a focus on Data and Analytics.
My career journey has provided me with the opportunity to delve into various aspects of data analysis and modelling, particularly within the BFSI sector, where I've managed the full lifecycle of development and execution.
I possess a diverse skill set that includes data wrangling, feature engineering, algorithm development, and model implementation. My expertise lies in leveraging advanced data mining techniques, such as statistical analysis, hypothesis testing, regression analysis, and both unsupervised and supervised machine learning, to uncover valuable insights and drive data-informed decisions. I'm especially passionate about risk identification through decision models, and I've honed my skills in machine learning algorithms, data/text mining, and data visualization to tackle these challenges effectively.
Currently, I am deeply involved in an exciting Amazon cloud project, focusing on the end-to-end development of ETL processes. I write ETL code using PySpark/Spark SQL to extract data from S3 buckets, perform necessary transformations, and execute scripts via EMR services. The processed data is then loaded into Postgres SQL (RDS/Redshift) in full, incremental, and live modes. To streamline operations, I’ve automated this process by setting up jobs in Step Functions, which trigger EMR instances in a specified sequence and provide execution status notifications. These Step Functions are scheduled through EventBridge rules.
Moreover, I've extensively utilized AWS Glue to replicate source data from on-premises systems to raw-layer S3 buckets using AWS DMS services. One of my key strengths is understanding the intricacies of data and applying precise transformations to convert data from multiple tables into key-value pairs. I’ve also optimized stored procedures in Postgres SQL to efficiently perform second-level transformations, joining multiple tables and loading the data into final tables.
I am passionate about harnessing the power of data to generate actionable insights and improve business outcomes. If you share this passion or are interested in collaborating on data-driven projects, I would love to connect. Let’s explore the endless possibilities that data analytics can offer!