Scribd
Upload
10 views5 pages

Financial Analytics Skill Development Activities - Edited

Uploaded by

Amal Jandheer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
10 views5 pages

Financial Analytics Skill Development Activities - Edited

Uploaded by

Amal Jandheer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

a) Different Types of Trends in Time Series Data

1. Additive vs. Multiplicative Trends:

• Additive: The trend rises or falls by a fixed amount (e.g., linear growth in sales).

• Multiplicative: The trend increases or decreases by a percentage (e.g., compounding interest).

The decision between the two is based on the characteristics of the data.

2. Periodic Trends:

Periodicity involves non-seasonal recurring patterns but happen at inconsistent intervals (e.g.,
economic expansions and contractions).

3. Irregular Trends:

These are typically influenced by outliers or infrequent events like natural disasters or political
upheaval.

4. Structural Breaks:

Sudden changes in trends result from significant events such as policy shifts, mergers, or
technological advancements.

b) Assumptions of Regressions (Expanded)

1. No Endogeneity:

The independent variables must not be associated with the error term. Endogeneity can arise
from missing variables, measurement inaccuracies, or reverse causality.

2. Non-Zero Variance:

Independent variables should exhibit variation; the regression model cannot compute coefficients
if they do not.
3. Outliers:

The presence of outliers in the dataset should be limited, as they can drastically affect the
regression line, leading to skewed results.

4. Error Independence:

Correlations among errors (e.g., when errors are related over time) violate this assumption,
especially in time-series regressions. Durbin-Watson tests can be used to evaluate this.

5. Model Simplicity:

To prevent overfitting, only include variables with a theoretical or empirical justification for
being part of the model.

c) Public Domain Databases (Expanded List)

1. Data.gov:

The U.S. government's open data platform has datasets covering finance, healthcare, and public
administration.

https://www.data.gov

2. Kaggle Datasets:

A broad array of datasets intended for machine learning and analytics projects, commonly
utilized in competitions.

https://www.kaggle.com/datasets

3. Eurostat:

Statistical information for European Union nations, encompassing economics, demographics,


and business data.

https://ec.europa.eu/eurostat
4. UN Data:

The United Nations offers access to global trade, economic, and development statistics.

https://data.un.org

5. OpenCorporates:

The largest open database of companies and their financial data globally.

https://opencorporates.com

6. Google Public Data Explorer:

Provides datasets in an interactive format suitable for analysis and visualization.

https://www.google.com/publicdata

d) Recent FinTech Companies (Expanded Insights)

1. Zest AI:

• Employs machine learning to evaluate credit risk for improved decision-making.

2. Brex:

• Focuses on providing financial tools for startups, including corporate credit cards and expense
tracking.

3. Blend:

• Delivers cloud-based software solutions for mortgage and consumer banking.

4. N26:
• A European challenger bank that provides an entirely digital banking experience.

5. Upstart:

• Utilizes AI to facilitate more informed credit choices and personal loans.

6. Paytm:

• A major Indian FinTech firm offering various services from payments to investment options.

7. Coinbase:

• A cryptocurrency exchange platform that has transformed the trading of digital assets.

8. Ant Financial (Alipay):

• A key player in China's FinTech space, providing payment, wealth management, and lending
services.

9. Tink:

• An open banking platform that allows companies to access financial data and services.

10. Betterment:

• An automated investment service focused on portfolio management and retirement planning.

Use Cases and Applications of Financial Analytics

1. Forecasting Sales and Revenue:

• Applying time series trends to estimate future streams of income.


2. Risk Assessment:

• Utilizing regression models to evaluate credit risks for individuals and organizations.

3. Portfolio Optimization:

• Examining trends and employing regression models to adjust investments.

4. Fraud Detection:

• Recognizing anomalies in transactions using time series and machine learning approaches.

5. Customer Segmentation:

• Leveraging public domain data to create customer profiles and customize financial products.

6. Economic Indicators Monitoring:

• Using databases like FRED and the World Bank to observe macroeconomic trends and predict
their influence on investments.

You might also like