← Home

Sustainable retirement age

AIM: assuming that the current situation of working / retired people is sustainable, and keeping that as reference, what is the retirement age for the whole century, considering the forecast model of the population I have built in my previous Notebook?

In [1]:
import json
import io
import numpy as np
import pandas as pd
import plotly.graph_objects as go
import plotly.io as pio


pio.renderers.default = 'plotly_mimetype+notebook'
pd.options.plotting.backend = "plotly"
In [2]:
dfp=pd.read_csv("../data/pop_by_age_year.csv", index_col=0).rename(columns=int) # From Notebook#14
In [3]:
retirement_age = pd.read_csv( # Digitized from source: https://www.linkedin.com/posts/federica-nerini-71222a2b0_a-che-et%C3%A0-si-va-in-pensione-in-italia-activity-7459644370825228288-lWXf
    io.StringIO("""
year,male,female
1974,62.1,59.7
1975,62.0,60.0
1976,62.0,60.4
1977,61.2,60.8
1978,60.9,60.7
1979,60.7,60.5
1980,60.8,60.4
1981,60.7,60.2
1982,60.9,61.0
1983,61.2,60.5
1984,61.1,60.2
1985,61.2,60.3
1986,60.9,60.0
1987,61.0,60.3
1988,60.5,60.1
1989,60.6,58.7
1990,60.7,58.2
1991,60.5,58.0
1992,59.5,57.5
1993,58.8,59.0
1994,58.5,58.8
1995,58.2,58.7
1996,58.2,58.5
1997,58.4,58.1
1998,58.3,57.9
1999,58.8,57.3
2000,59.2,57.2
2001,59.0,58.2
2002,59.5,58.9
2003,59.9,58.0
2004,60.0,58.1
2005,59.9,57.9
2006,60.2,57.8
2007,60.4,57.8
2008,60.5,57.8
2009,60.0,57.9
2010,59.7,58.6
2011,60.1,58.9
2012,60.5,60.1
2013,60.5,60.2
2014,60.8,59.8
2015,60.9,60.2
2016,61.2,60.7
2017,61.5,60.7
2018,62.3,61.0
2019,62.8,61.9
2020,62.6,61.5
2021,62.3,61.5
2022,62.7,61.8
2023,63.1,62.2
""".strip()))

retirement_age["average"] = retirement_age[["male", "female"]].mean(axis=1)
(
    retirement_age
    .plot(x="year", y=["male", "female", "average"])
    .update_layout(
        title="Effective retirement age in Italy (source: OCSE)",
        width=800
        )
    .show()
)

Visualize the past distribution of working / retired people, to spot some ratio to keep as reference for the future.

In [4]:
# I'm making some assumptions on the average age of retirement and start working
first_year = dfp.columns[0]
last_year = dfp.columns[-1]
print("First and last year in the dataset:", first_year, last_year)

past_retirement_lookup = retirement_age.set_index("year")["average"].to_dict()

working_age = { y: 18 + 4*(y-first_year)/(last_year-first_year) for y in dfp.columns } # Assumption: it was 18 in first year and 22 in last
retirem_age = { y: past_retirement_lookup.get(y, 61 if y < 1980 else 64) for y in dfp.columns } # Assumption: following the retirement_age data

# ratio of people in working age over retired age
wr_df = pd.DataFrame(index=dfp.columns)
wr_df["working-age / retirement-age ratio"] = np.nan
for y in wr_df.index:
    wa = working_age[y]
    ra = retirem_age[y]
    wr_df.loc[y, "working-age / retirement-age ratio"] = dfp.loc[wa:ra,y].sum() / dfp.loc[ra:,y].sum()
    
wr_df.plot().update_layout(
    xaxis_title="Year",
    yaxis_title="Working-age / Retirement-age ratio",
    showlegend=False,
    height=500,
    width=800,
).show()
First and last year in the dataset: 1952 2026
In [5]:
# Compute the mean wr ratio, but only the recent one, which seems stabilized
starting_year_mean = 2000
wr_ratio = wr_df.loc[wr_df.index >= starting_year_mean, "working-age / retirement-age ratio"].mean().round(2)
print(f"Mean working-age/retirement ratio since {starting_year_mean}:", wr_ratio)
Mean working-age/retirement ratio since 2000: 2.06
In [6]:
dfs = pd.read_csv("../data/pop_by_age_year_proj.csv", index_col=0)
dfp_projs = {
    scenario: ( # convert to the usual dataframe age-x-year format
        dfs
        .reset_index()
        [["year", "AGE", scenario]]
        .pivot(index="year", columns="AGE", values=scenario)
        .transpose()
    )
    for scenario in dfs.columns[1:]
}

The reference working-age / retirement-age population ratio is computed above from observations since 2000. This demographic proxy assumes constant employment and does not estimate pension finances, wages or contribution income.

In [7]:
past_retirement_cohort = (
    retirement_age
    .assign(Born_year_retiring=lambda df: (df.year - df.average).astype(int))
    .sort_values("Born_year_retiring")
)
past_retirement_cohort
Out[7]:
year male female average Born_year_retiring
0 1974 62.1 59.7 60.90 1913
1 1975 62.0 60.0 61.00 1914
2 1976 62.0 60.4 61.20 1914
3 1977 61.2 60.8 61.00 1916
4 1978 60.9 60.7 60.80 1917
5 1979 60.7 60.5 60.60 1918
6 1980 60.8 60.4 60.60 1919
7 1981 60.7 60.2 60.45 1920
8 1982 60.9 61.0 60.95 1921
9 1983 61.2 60.5 60.85 1922
10 1984 61.1 60.2 60.65 1923
11 1985 61.2 60.3 60.75 1924
12 1986 60.9 60.0 60.45 1925
13 1987 61.0 60.3 60.65 1926
14 1988 60.5 60.1 60.30 1927
15 1989 60.6 58.7 59.65 1929
16 1990 60.7 58.2 59.45 1930
17 1991 60.5 58.0 59.25 1931
18 1992 59.5 57.5 58.50 1933
19 1993 58.8 59.0 58.90 1934
20 1994 58.5 58.8 58.65 1935
21 1995 58.2 58.7 58.45 1936
22 1996 58.2 58.5 58.35 1937
23 1997 58.4 58.1 58.25 1938
24 1998 58.3 57.9 58.10 1939
25 1999 58.8 57.3 58.05 1940
26 2000 59.2 57.2 58.20 1941
27 2001 59.0 58.2 58.60 1942
28 2002 59.5 58.9 59.20 1942
29 2003 59.9 58.0 58.95 1944
30 2004 60.0 58.1 59.05 1944
31 2005 59.9 57.9 58.90 1946
32 2006 60.2 57.8 59.00 1947
33 2007 60.4 57.8 59.10 1947
34 2008 60.5 57.8 59.15 1948
35 2009 60.0 57.9 58.95 1950
36 2010 59.7 58.6 59.15 1950
37 2011 60.1 58.9 59.50 1951
38 2012 60.5 60.1 60.30 1951
39 2013 60.5 60.2 60.35 1952
40 2014 60.8 59.8 60.30 1953
41 2015 60.9 60.2 60.55 1954
42 2016 61.2 60.7 60.95 1955
43 2017 61.5 60.7 61.10 1955
44 2018 62.3 61.0 61.65 1956
45 2019 62.8 61.9 62.35 1956
46 2020 62.6 61.5 62.05 1957
47 2021 62.3 61.5 61.90 1959
48 2022 62.7 61.8 62.25 1959
49 2023 63.1 62.2 62.65 1960
In [8]:
# Same data plotted in two variants

fig = go.Figure()
retirement_summary = {"reference_ratio": float(wr_ratio), "reference_years": [starting_year_mean, int(last_year)], "birth_year": 1990, "scenarios": {}}
# Export calendar-year ages for notebook 86, preserving the assumptions above.
annual_retirement_records = [
    {"year": int(y), "scenario": "Historical / current", "retirement_age": float(retirem_age[y]),
     "retirement_age_source": "observed effective age" if y in past_retirement_lookup else "assumed age"}
    for y in dfp.columns
]
for scenario_label, dfpproj in dfp_projs.items():
    raproj_df = pd.DataFrame(index=range(2002,2100+1))
    raproj_df["Sustainable retirement age"] = np.nan
    for y in raproj_df.index:
        wa = 22 # Assumption: people will start working at 22 on average
        for ra in range(50, 100): # I'm testing different retirement ages (ra) untill the wr_ratio is reached
            if dfpproj.loc[wa:ra,y].sum() / dfpproj.loc[ra:,y].sum() > wr_ratio:
                raproj_df.loc[y, "Sustainable retirement age"] = ra - 1 
                break
        
    raproj_df["Born year retiring"] = raproj_df.index - raproj_df["Sustainable retirement age"]
    raproj_df = (
        raproj_df
        .reset_index()
        .rename(columns={"index": "Year of Retirement"})
        .astype(int)
    )
    annual_retirement_records.extend(
        {"year": int(row["Year of Retirement"]), "scenario": scenario_label,
         "retirement_age": int(row["Sustainable retirement age"]),
         "retirement_age_source": "projected demographic proxy"}
        for _, row in raproj_df.loc[raproj_df["Year of Retirement"] > last_year].iterrows()
    )
    cohort = raproj_df.loc[raproj_df["Born year retiring"] == 1990]
    if not cohort.empty:
        retirement_summary["scenarios"][scenario_label] = {
            "retirement_age_min": int(cohort["Sustainable retirement age"].min()),
            "retirement_age_max": int(cohort["Sustainable retirement age"].max()),
            "retirement_year_min": int(cohort["Year of Retirement"].min()),
            "retirement_year_max": int(cohort["Year of Retirement"].max()),
        }
    fig.add_trace(
        go.Scatter(
        x=raproj_df["Born year retiring"],
        y=raproj_df["Sustainable retirement age"],
        mode='lines',
        text=[f'With scenario `{scenario_label}` <br>someone born in {raproj_df.at[i, "Born year retiring"]} will retire in {raproj_df.at[i, "Year of Retirement"]} at {raproj_df.at[i, "Sustainable retirement age"]}yo'
              for i in raproj_df.index],
        hoverinfo='text',
        name=scenario_label
    ))   
fig.add_trace(
    go.Scatter(
    x=past_retirement_cohort["Born_year_retiring"],
    y=past_retirement_cohort["average"],
    mode='lines',
    text=[f'Past data <br>someone born in {past_retirement_cohort.at[i, "Born_year_retiring"]} retired on average in {past_retirement_cohort.at[i, "year"]} at {past_retirement_cohort.at[i, "average"]:.0f}yo'
          for i in past_retirement_cohort.index],
    hoverinfo='text',
    name="Past effective retirement age",
    line=dict(color='black', width=2)
))  
fig.update_layout(
    xaxis_title="Year of Birth",
    yaxis_title="Retirement Age",
    legend_title="Scenarios",
    showlegend=True,
    margin=dict(l=0, r=15, t=20, b=0),
    width=780,
    height=320,
)
print(f"Sustainable retirement age to maintain the same ratio of working/retired people of {wr_ratio:.2f}:")
fig.write_html("../images_output/sust_retirement_age.html")
fig.show()
with open("../data/retirement_summary.json", "w") as output:
    json.dump(retirement_summary, output, indent=2)
display(retirement_summary)

# One historical/current row per year, then all nine scenarios after the population baseline.
pd.DataFrame(annual_retirement_records).to_csv("../data/retirement_age_by_year.csv", index=False)
Sustainable retirement age to maintain the same ratio of working/retired people of 2.06:
{'reference_ratio': 2.06,
 'reference_years': [2000, 2026],
 'birth_year': 1990,
 'scenarios': {'migr double  & fert ↑ 2 in 2100': {'retirement_age_min': 67,
   'retirement_age_max': 67,
   'retirement_year_min': 2057,
   'retirement_year_max': 2057},
  'migr double  & fert eq. to last': {'retirement_age_min': 67,
   'retirement_age_max': 67,
   'retirement_year_min': 2057,
   'retirement_year_max': 2057},
  'migr double  & fert ↓ 0 in 2100': {'retirement_age_min': 67,
   'retirement_age_max': 67,
   'retirement_year_min': 2057,
   'retirement_year_max': 2057},
  'migr average & fert ↑ 2 in 2100': {'retirement_age_min': 69,
   'retirement_age_max': 69,
   'retirement_year_min': 2059,
   'retirement_year_max': 2059},
  'migr average & fert eq. to last': {'retirement_age_min': 69,
   'retirement_age_max': 69,
   'retirement_year_min': 2059,
   'retirement_year_max': 2059},
  'migr average & fert ↓ 0 in 2100': {'retirement_age_min': 69,
   'retirement_age_max': 69,
   'retirement_year_min': 2059,
   'retirement_year_max': 2059},
  'migr zero    & fert ↑ 2 in 2100': {'retirement_age_min': 72,
   'retirement_age_max': 72,
   'retirement_year_min': 2062,
   'retirement_year_max': 2062},
  'migr zero    & fert eq. to last': {'retirement_age_min': 72,
   'retirement_age_max': 72,
   'retirement_year_min': 2062,
   'retirement_year_max': 2062},
  'migr zero    & fert ↓ 0 in 2100': {'retirement_age_min': 72,
   'retirement_age_max': 72,
   'retirement_year_min': 2062,
   'retirement_year_max': 2062}}}

Conclusions

  • The reference ratio is the observed average of working-age to retirement-age residents since 2000, using the historical age assumptions above.
  • The current scenario results for the 1990 birth cohort are shown above and saved in data/retirement_summary.json.
  • These are demographic scenario comparisons. They do not predict statutory retirement ages or measure pension finances: employment, wages, productivity, contributions and benefits are outside this model.
  • The start-of-work age remains 22 in future years; sensitivity to that assumption and the reference ratio remains future work.
← Home