Modeldrift

Forecasting-pijplijnen ontwerpen voor productie

Rami Krispin

Senior Manager, Data Science and Engineering

Modeldrift

Modelprestaties nemen af in de tijd 📉

Vaak veroorzaakt door conceptdrift

Oude modellen raken uit lijn ❌

Modeldrift

Conceptdrift

Andere oorzaken van modeldrift

Modellevenscyclus

Pijplijn-levenscyclus

Detecteer modeldrift

Modeldrift detecteren

Detecteer modeldrift

Voorspellingsnauwkeurigheid volgen

Drift vaststellen

import pandas as pd
import plotly.graph_objects as go

fc_log = pd.read_csv("./data/us48_forecast_log.csv")


fc_log["mape_ma_7"] = fc_log["mape"].rolling(window = 7).mean()
fc_log["mape_ma_14"] = fc_log["mape"].rolling(window = 14).mean()

Drift vaststellen

print(fc_log[["mape_ma_7","mape_ma_14"]].tail(10))

     mape_ma_7  mape_ma_14
120   0.054181    0.043237
121   0.062931    0.047272
122   0.063285    0.045938
123   0.058811    0.046456
124   0.060165    0.046120
125   0.055948    0.045952
126   0.043080    0.045459
127   0.035748    0.044965
128   0.028009    0.045470
129   0.025801    0.044543

Drift vaststellen

threshold = 3

Drift vaststellen

threshold = 3

# Setting plotly figure
p = go.Figure()
# Add the model performance (MAPE) over time
p.add_trace(go.Scatter(x = fc_log["forecast_start"], y = 100 * fc_log["mape"],
                        mode="lines",
                        name="MAPE",
                        line=dict(color='royalblue', width=2)))
# Setting the plots layout
p.update_layout(title = "Forecast Error Rate Over Time", 
               xaxis_title="Model Error Rate Since Deployment",
               yaxis_title="MAPE (%)")

Drift vaststellen

# Adding the threshold  and 7 and 14 rolling windows
p.add_shape(type="line",
              x0=fc_log["forecast_start"].min(), x1=fc_log["forecast_start"].max(),
              y0=threshold, y1=threshold,
              line=dict(color="red", width=2, dash = "dash"))

p.add_trace(go.Scatter(x = fc_log["forecast_start"], y = 100 * fc_log["mape_ma_7"],
                        mode="lines",name="7 Days MA",
                        line=dict(color="green", width=2)))

p.add_trace(go.Scatter(x = fc_log["forecast_start"], y = 100 * fc_log["mape_ma_14"],
                        mode="lines",name="14 Days MA",
                        line=dict(color="orange", width=2)))


p.show()

Drift vaststellen

Laten we oefenen!

Forecasting-pijplijnen ontwerpen voor productie