Update README.md

README.md

@@ -12,6 +12,11 @@ co2_eq_emissions:
   emissions: 0.004371975254312265
 ---
 
+
+# Model Trained Using AutoTrain
+We trained FinBERT to identify whether firms´ talk contains consumer concepts of human nature (e.g., "I believe consumers generally act rational.", "Consumers must take over responsibility for the choices they make.", "It seems consumers behave quite altruistic.") from statements that do not (e.g., "We expect buyers to double their purchases next year.").  
+The training data was comprised of 236 positive documents (containing concepts of consumer nature) and 1034 negative documents (not contain concepts of consumer nature) extracted from earnings call transcripts of S&P-500 companies (2015-2020).
+
 # Model Trained Using AutoTrain
 
 - Problem type: Binary Classification