Fundamental economic conditions are crucial determinants of equity premia. However, commonly used predictors do not adequately capture the changing nature of economic conditions and hence have limited power in forecasting equity returns. To address the inadequacy, this paper constructs macro indexes from large data sets and adaptively chooses optimal indexes to predict stock returns. I find that adaptive macro indexes explain a substantial fraction of the short-term variation in future stock returns and have more forecasting power than both the historical average of stock returns and commonly used predictors. The forecasting power exhibits a strong cyclical pattern, implying the ability of adaptive macro indexes to capture time-varying economic conditions. This finding highlights the importance of using dynamically measured economic conditions to investigate empirical linkages between the equity premium and macroeconomic fundamentals.