Time Series Analysis on FDIC Bank Failures

CREATE TABLE bank_failures (
id bigserial,
bank_name TEXT,
city TEXT,
state TEXT,
cert TEXT,
acquiring_institution TEXT,
closing_date DATE,
fund BIGINT
);

COPY bank_failures (
bank_name,
city,
state,
cert,
acquiring_institution,
closing_date,
fund
) FROM '/path/to/banklist.csv' WITH (FORMAT csv, DELIMITER ',', QUOTE '"', ESCAPE '"', ENCODING 'UTF-8');

-- Return bank failures by month, year based on the dataset
 SELECT
  EXTRACT('YEAR' FROM closing_date :: DATE) as closing_year, 
  EXTRACT('MONTH' FROM closing_date :: DATE) as closing_month, 
  COUNT(*) as total_failures  
FROM bank_failures 
GROUP BY closing_year, closing_month
ORDER BY closing_year, closing_month;

-- Generate a row for every month between Jan, 2000 and Dec, 2023
SELECT generate_series('2000-01-01', '2023-12-01','1 month'::interval) as timescale;

-- Generate a row for every year between Jan, 2000 and Dec, 2023
SELECT generate_series('2000-01-01', '2023-12-01','1 year'::interval) as timescale;

-- Return bank failures by month, year based on the dataset
with series as (SELECT
generate_series('2000-01-01', '2023-12-01','1 month'::interval) as timescale)
SELECT
  EXTRACT('YEAR' FROM timescale) as closing_year, 
  EXTRACT('MONTH' FROM timescale) as closing_month, 
  COUNT(bank_failures.closing_date) as total_failures  
-- the series table has complete dates, so join bank_failures onto the series for complete data for the complete time period
FROM series LEFT JOIN bank_failures 
on EXTRACT('YEAR' from timescale) = EXTRACT('YEAR' from closing_date :: DATE)
and EXTRACT('MONTH' from timescale) = EXTRACT('MONTH' from closing_date :: DATE)
GROUP BY closing_year, closing_month
ORDER BY closing_year, closing_month;

with series as (SELECT
generate_series('2000-01-01', '2023-12-01','1 year'::interval) as timescale)
SELECT
  EXTRACT('YEAR' FROM timescale) as closing_year, 
  COUNT(bank_failures.closing_date) as total_failures  
FROM series LEFT JOIN bank_failures 
on EXTRACT('YEAR' from timescale) = EXTRACT('YEAR' from closing_date :: DATE)
GROUP BY closing_year
ORDER BY closing_year;

create materialized view bank_failures_by_month as (
with series as (SELECT
generate_series('2000-01-01', '2023-12-01','1 month'::interval) as timescale)
SELECT
  EXTRACT('YEAR' FROM timescale) as closing_year, 
  EXTRACT('MONTH' FROM timescale) as closing_month, 
  COUNT(bank_failures.closing_date) as total_failures  
FROM series LEFT JOIN bank_failures 
on EXTRACT('YEAR' from timescale) = EXTRACT('YEAR' from closing_date :: DATE)
and EXTRACT('MONTH' from timescale) = EXTRACT('MONTH' from closing_date :: DATE)
GROUP BY closing_year, closing_month
ORDER BY closing_year, closing_month);

select count(*) from bank_failures bf ;

select 
    state, 
    COUNT(*) as bank_failures
from bank_failures bf 
group by state
order by COUNT(*) desc
limit 10;

select 
    state, 
    extract('YEAR' from closing_date) :: TEXT as closing_year, 
    COUNT(*) as state_failures_by_year
from bank_failures bf 
group by state, extract('YEAR' from closing_date) 
order by COUNT(*) desc
limit 10;

with ranked_state_failures_by_year as (
    select 
     extract('YEAR' from closing_date) as closing_year,
     state,
     COUNT(*) as state_failures_by_year,
     -- Window functions are evaluated AFTER the group by clause, so this is comparing the bank failures per state
     dense_rank() over (partition by extract('YEAR' from closing_date) order by  COUNT(*) desc) 
    from bank_failures bf 
    group by extract('YEAR' from closing_date), state
    order by extract('YEAR' from closing_date), COUNT(*) desc),
all_years as (
    select generate_series('01-01-2000', '01-01-2023', '1 year'::interval) as timescale
)
select 
    extract('YEAR' from all_years.timescale) as closing_year, 
    coalesce(state, 'N/A') as state, 
    coalesce(state_failures_by_year, 0) as state_failures_by_year
from 
all_years left JOIN
ranked_state_failures_by_year
on  extract('YEAR' from all_years.timescale) = ranked_state_failures_by_year.closing_year 
-- Some years do not have bank failures, so we include a null check to ensure they appear in the result set
where dense_rank = 1 or dense_rank is null
order by all_years.timescale;

select 
    RANK() over (order by sum(total_failures) desc),
    closing_year::int, 
    SUM(total_failures) as total_failures
from bank_failures_by_month 
group by closing_year
order by SUM(total_failures) desc
limit 5;

select 
    RANK() over (order by total_failures desc),
    closing_year :: INT, 
    closing_month,
    total_failures
from bank_failures_by_month 
order by total_failures desc
limit 5;

with bank_failures_by_year as (
-- Return a table with the year, total_failures, and toal failures in the previous year, defaulting to 0 if not data is found
SELECT
  EXTRACT('YEAR' FROM timescale) as closing_year, 
  COUNT(bank_failures.closing_date) as total_failures,
  coalesce(LAG(COUNT(bank_failures.closing_date)) over (order by EXTRACT('YEAR' FROM timescale)),0) as prev_year_failures
FROM (SELECT
generate_series('2000-01-01', '2023-12-01','1 year'::interval) as timescale) as series LEFT JOIN bank_failures 
-- Join the series of years with the bank failures table based on matching years
on EXTRACT('YEAR' from timescale) = EXTRACT('YEAR' from closing_date)
GROUP BY closing_year
ORDER BY closing_year)
-- Calculate the year over year change between each year of bank failures
select closing_year, total_failures, 
    case 
        when closing_year = 2000 then 'N/A'
        when prev_year_failures = total_failures  then '0%'
        when prev_year_failures  = 0 then 'N/A'
        else ROUND(((total_failures - prev_year_failures) :: NUMERIC / prev_year_failures) * 100.0, 2) || '%' 
    end as yoy_pct_change
from bank_failures_by_year;