HAND-OUT IN DATA SCIENCE ANALYTICS (FINALS)
Time-based Data is also referred to time series data ---- is defined as a collection of data points measured or
recorded at successive points in time.
Key characteristic of Time Series Data:
chronological order
This ordering enables:
the identification of trends
seasonal patterns
& other temporal dynamics within the dataset
Key Features of Time Series Data:
Temporal Dependency --- This dependency is vital for forecasting and understanding underlying
processes.
Regular Intervals --- Time series data is typically collected at regular intervals (e.g., hourly, daily,
monthly) which facilitates analysis and modeling.
Components --- Time series data can exhibit various components:
Trend - Long-term movement in the data (increasing or decreasing).
Seasonality - Regular fluctuations that occur at specific intervals (e.g., monthly sales
spikes during holidays).
Cyclical Patterns - Longer-term fluctuations that are not fixed in frequency, often
influenced by economic cycles.
Applications of Time Series Data:
Time series data is utilized across numerous fields for various applications:
Finance: Analyzing stock prices to identify trends and make investment decisions.
Weather Forecasting: Using historical weather data to predict future conditions.
Healthcare: Monitoring patient vitals over time to detect anomalies or health issues.
Retail Analytics: Examining sales data to optimize inventory and marketing strategies
Techniques in Time Series Analysis
Decomposition: Breaking down a time series into its constituent components (trend,
seasonality, residuals) for better understanding.
Smoothing Techniques: Applying methods like moving averages to reduce noise and highlight
trends.
Statistical Tests: Conducting tests such as the Augmented Dickey-Fuller test to check for
stationarity before modeling
Time series charts ---- are graphical representations that display data points in chronological order. They
are used to visualize how a variable changes over time, making it easier to identify trends, seasonal
patterns, and anomalies.
Types of time series charts include:
Line Charts: These charts connect individual data points with lines, effectively showing trends
over time.
Bar Charts: Useful for comparing quantities at different time intervals.
Area Charts: Similar to line charts but filled with color below the line to emphasize the volume
of data.
Key Features:
X-axis: Represents time (e.g., days, months, years).
Y-axis: Represents the variable being measured (e.g., sales, temperature).
Trend Identification: Helps in spotting upward or downward trends and cyclical patterns.
Forecasting models ---- are statistical tools that predict future events based on historical data. They
analyze past patterns to project future outcomes, which is crucial for decision-making in businesses and
other sectors.
Two main types of forecasting models:
Qualitative Models: These rely on subjective judgment and expert opinions (e.g., the Delphi
method) and are often used when historical data is scarce or when predicting new trends.
Quantitative Models: These use mathematical and statistical techniques to analyze numerical
data.
Common quantitative forecasting models include:
Time Series Models: Analyze historical data to predict future values. Examples include:
Moving Average Model: Smooths out fluctuations by averaging data over a specific period.
Exponential Smoothing: Assigns more weight to recent observations to make short-term
forecasts.
ARIMA (AutoRegressive Integrated Moving Average): Captures trends and seasonality by using
past values and errors in predictions.
Econometric Models: Use economic theories and relationships between variables to forecast
outcomes.
In terms of Application:
Forecasting models are utilized across various industries for purposes such as:
Predicting sales and inventory levels.
Analyzing financial markets.
Planning resource allocation in healthcare.
Activity: (ESSAY) – 50 points
From the whole part of Data Science Analytics, what particular lesson or topic catches your
attention and why?
How did this topic changed your perception in Data Science Analytics (comparing to your
expectation to the subject beforehand)
Rubrics:
Introduction (2 points) – your intro.
Time Series Charts (10 points) – ano yung mga ilalagay mong topics sa x axis or y axis
Forecasting Models (10 points) – anong model gagamitin mo as example to portray your asnwer
Conclusion (3 points) – Recap the main points, ano kana pagkatapos ng DSA, nafo-foresee mong
future.
Clarity and Structure (25) - Ensure that the essay has a clear structure, Use appropriate
academic language, avoiding jargons
